[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-lixus7--Time-Series-Works-Conferences":3,"tool-lixus7--Time-Series-Works-Conferences":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",152630,2,"2026-04-12T23:33:54",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":79,"owner_website":79,"owner_url":80,"languages":79,"stars":81,"forks":82,"last_commit_at":83,"license":84,"difficulty_score":85,"env_os":86,"env_gpu":87,"env_ram":87,"env_deps":88,"category_tags":91,"github_topics":92,"view_count":111,"oss_zip_url":79,"oss_zip_packed_at":79,"status":17,"created_at":112,"updated_at":113,"faqs":114,"releases":145},2059,"lixus7\u002FTime-Series-Works-Conferences","Time-Series-Works-Conferences","Time-Series Work Summary in CS Top Conferences (NIPS, ICML, ICLR, KDD, AAAI, WWW, IJCAI, CIKM, ICDM, ICDE, etc.)","Time-Series-Works-Conferences 是一个专注于时间序列分析领域的学术资源汇总项目。它系统地梳理并收录了发表在 NeurIPS、ICML、ICLR、KDD、AAAI 等计算机科学顶级会议上的相关论文与代码实现。\n\n面对时间序列研究文献爆炸式增长、优质资源分散难寻的痛点，该项目通过将海量论文按“任务类型”和“方法论”进行双重分类整理，帮助研究者快速定位前沿成果。它不仅提供了清晰的会议年份索引（涵盖已发表及待更新的 AAAI、ICML 等未来会议），还整理了包括轨迹预测在内的多个细分方向资源，甚至提供了论文与代码的云端存储链接，极大降低了资料获取门槛。\n\n这款工具特别适合人工智能领域的研究人员、博士生以及从事时序数据分析的算法工程师使用。无论是想要追踪最新学术动态、寻找实验基线模型，还是希望系统了解某一特定方法的发展脉络，都能从中获得高效支持。其独特的亮点在于持续维护的更新机制与结构化的知识体系，由来自新南威尔士大学的研究团队主导，鼓励社区通过 Issue 或 Pull Request 共同完善，确保了内容的时效性与准确性，是时间序列领域不可或缺的案头参考库。","# Time-Series Works and Conferences\n\n# Backlog (To do): AAAI2025, ICML2025, AAAI2026, ICLR2026...\n\n\u003C!-- **Visit our [GitHub Page](https:\u002F\u002Flixus7.github.io\u002FTime-Series-Works-Conferences\u002F) for a better view.**\n\n\n\u003Ca href=\"#Conferences\">Click here to jump to the Conferences page with more conference information.\u003C\u002Fa>\n\nor [AI ML Summary Github](https:\u002F\u002Fgithub.com\u002FLionelsy\u002FConference-Accepted-Paper-List)\n\nSome other nice time-series repositories:\n\n[xiyuanzh\u002Ftime-series-papers](https:\u002F\u002Fgithub.com\u002Fxiyuanzh\u002Ftime-series-papers)\n\n[qingsongedu\u002Fawesome-AI-for-time-series-papers](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)\n\n[xuehaouwa\u002FAwesome-Trajectory-Prediction](https:\u002F\u002Fgithub.com\u002Fxuehaouwa\u002FAwesome-Trajectory-Prediction)\n\n[My Time-series Repo-Star List](https:\u002F\u002Fgithub.com\u002Fstars\u002Flixus7\u002Flists\u002Ftime-series-list) -->\n\n\u003Cdiv align=\"center\">\n\u003C!-- \u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F54fdbe8888c0a75717d7939b42f3d744b77483b0\u002F687474703a2f2f6a617977636a6c6f76652e6769746875622e696f2f73622f69636f2f617765736f6d652e737667\" \u002F>\n\u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F1ef04f27611ff643eb57eb87cc0f1204d7a6a14d\u002F68747470733a2f2f696d672e736869656c64732e696f2f7374617469632f76313f6c6162656c3d254630253946253843253946266d6573736167653d496625323055736566756c267374796c653d7374796c653d666c617426636f6c6f723d424334453939\" \u002F>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F41e8e16b771d56dd768f7055354613254961d169\u002F687474703a2f2f6a617977636a6c6f76652e6769746875622e696f2f73622f6769746875622f677265656e2d666f6c6c6f772e737667\" \u002F> \u003C\u002Fa> -->\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Flixus7\u002FTime-Series-Works-Conferences\" \u002F> \u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fnetwork\u002Fmembers\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flixus7\u002FTime-Series-Works-Conferences\" \u002F> \u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fstargazers\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flixus7\u002FTime-Series-Works-Conferences\" \u002F> \u003C\u002Fa>\n\u003C!-- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fblob\u002Fmain\u002Fdocs\u002Fimg\u002FWeChat.jpeg\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F013c283843363c72b1463af208803bfbd5746292\u002F687474703a2f2f6a617977636a6c6f76652e6769746875622e696f2f73622f69636f2f7765636861742e737667\" \u002F> \u003C\u002Fa> -->\n\u003C\u002Fdiv>\n\n\u003C!-- \n\n\n> I have a strong interest in time-series research. Welcome to contact me for discussions and collaborative efforts.\n\u003Cbr> I am currently pursuing a doctoral degree in CSE of UNSW, Sydney, under the supervision of Prof. [Flora Salim](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=Yz35RSYAAAAJ&hl=zh-CN&oi=ao) and [Hao Xue](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=KwhLl7IAAAAJ&hl=zh-CN&oi=ao). I got the master degree under the supervision of Prof. [Xuan Song](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=_qCSLpMAAAAJ&hl=zh-CN&oi=ao), [Quanjun Chen](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=_PKwzTwAAAAJ&hl=zh-CN) and [Renhe Jiang](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=Yo2lwasAAAAJ&hl=zh-CN&oi=ao).\n\n\n\nThe task section has been completed and we will continue to update the methodology section. If you encounter any missing resources (papers\u002Fcode) or errors, please don't hesitate to open an issue or make a pull request. Additionally, if you're interested in collaborating on this work, please feel free to contact me.\n\nAll papers are organized by task and methodology, including those not included in this GitHub repository, and are available for everyone to use on OneDrive and Google Drive (VPN required). \n\n[OneDrive](https:\u002F\u002F1drv.ms\u002Fu\u002Fs!Au2cJRs-_u93lDbLrSDkDy8htv2V?e=ftuaXd)\n \n[Google Drive](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F17bILWdDxUrufRp3yilYfoU5VKywwS1g6?usp=sharing)\n\n\n\n\nTo reduce repetition, some data are in abbreviated form. Some terms may not represent general interpretations and apply only to this repository.\n\n|Full Name | Abbreviation|\n|:--|:--|\n| Adaptive GNN | AGNN |\n| Attention | Attn | \n| AutoRegression(RNN,GRU,LSTM) | AR |\n| Controlled Differential Equations | CDE | \n| Contrastive Learning | CL |\n| Encoder Decoder | EncDec | \n| Ensemble | Ens |\n| Feature Decomposed | FeaD |\n| Federated Learning | FL | \n| Generative Adversarial Network | GAN |\n| Graph Convolutional Network | GCN | \n| Hour, Day, Week, Month, etc | HA |\n| Heterogeneous GNN | HGNN |\n| Multiple Graph | MGNN |\n| Memory | Mem | \n| Meta Learning | MetaL | \n| MultiTask | MulT | \n| Network Architechture Search | NAS | \n| Ordinary Differential Equations | ODE |\n| Statistic | Stat |\n| TCN (WaveNet) | TCN | \n| Temporal Graph Network | TGN | \n| Transformer | Trans | \n| Transfer Learning | TransL | \n| Variational Auto-Encoder | VAE | -->\n\n# Recent Time Series Works Grouped by Task\n\n- \u003Ca href = \"#Multivariat-Time-Series-Forecasting\">Multivariat Time Series Forecasting\u003C\u002Fa>\n- \u003Ca href = \"#Multivariat-Probabilistic-Time-Series-Forecasting\">Multivariat Probabilistic Time Series Forecasting\u003C\u002Fa>\n- \u003Ca href = \"#Time-Series-Imputation\">Time Series Imputation\u003C\u002Fa>\n- \u003Ca href = \"#Time-Series-Anomaly-Detection\">Time Series Anomaly Detection\u003C\u002Fa>\n- \u003Ca href = \"#Demand-Prediction\">Demand Prediction\u003C\u002Fa>\n- \u003Ca href = \"#Time-Series-Generation\">Time Series Generation\u003C\u002Fa>\n- \u003Ca href = \"#Travel-Time-Estimation\">Travel Time Estimation\u003C\u002Fa>\n- \u003Ca href = \"#Traffic-Location-Prediction\">Traffic Location Prediction\u003C\u002Fa>\n- \u003Ca href = \"#Event-Prediction\">Event Prediction\u003C\u002Fa>\n- \u003Ca href = \"#Stock-Prediction\">Stock Prediction\u003C\u002Fa>\n- \u003Ca href = \"#Other-Forecasting\">Other Forecasting\u003C\u002Fa>\n\n \n\n# [Multivariat Time Series Forecasting](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| \u003Cimg width=10> | \u003Cimg width=10\u002F> | \u003Cimg width=10\u002F> | \u003Cimg width=100\u002F> | | \u003Cimg width=500\u002F> |\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LightGTS | [LightGTS: A Lightweight General Time Series Forecasting Model](https:\u002F\u002Fopenreview.net\u002Fforum?id=Z5FJsp1U3Z¬eId=5N5JjGUW0m) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FLightGTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FLightGTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FLightGTS?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LETS | [LETS Forecast: Learning Embedology for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=LLk1qYQatJ) | [Code](https:\u002F\u002Fgithub.com\u002Fabrarmajeedi\u002FDeepEDM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fabrarmajeedi\u002FDeepEDM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fabrarmajeedi\u002FDeepEDM?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeBase | [TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=GhTdNOMfOD) | [Code](https:\u002F\u002Fgithub.com\u002Fhqh0728\u002FTimeBase) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhqh0728\u002FTimeBase?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhqh0728\u002FTimeBase?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | RAFT | [Retrieval Augmented Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=GUDnecJdJU) | [Code](https:\u002F\u002Fgithub.com\u002Farchon159\u002FRAFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Farchon159\u002FRAFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Farchon159\u002FRAFT?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CN | [Channel Normalization for Time Series Channel Identification](https:\u002F\u002Fopenreview.net\u002Fforum?id=PqpPrlAQqa) | [Code](https:\u002F\u002Fgithub.com\u002Fseunghan96\u002FCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseunghan96\u002FCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fseunghan96\u002FCN?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeBridge | [TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=pyKO0ZZ5lz) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FTimeBridge) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FTimeBridge?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FTimeBridge?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeStacker | [TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=5RYSqSKz9b) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FTimeBridge) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FTimeBridge?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FTimeBridge?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | WaveToken | [Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization](https:\u002F\u002Fopenreview.net\u002Fforum?id=B6WalMoQJW) | [Code](https:\u002F\u002Fgithub.com\u002Famazon-science\u002Fchronos-forecasting\u002Ftree\u002Fwavetoken) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Moirai-MoE | [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https:\u002F\u002Fopenreview.net\u002Fforum?id=SrEOUSyJcR) | [Code](https:\u002F\u002Fgithub.com\u002FSalesforceAIResearch\u002Funi2ts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSalesforceAIResearch\u002Funi2ts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSalesforceAIResearch\u002Funi2ts?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [In-Context Fine-Tuning for Time-Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=uxzgGLWPj2) | None | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SKOLR | [SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Xg1BGlybfq) | [Code](https:\u002F\u002Fgithub.com\u002Fnetworkslab\u002FSKOLR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnetworkslab\u002FSKOLR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnetworkslab\u002FSKOLR?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | ECL \u003Cbr> Nottingham | FSTLLM | [FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=oyoiHf51es) | [Code](https:\u002F\u002Fgithub.com\u002FJIANGYUE61610306\u002FFSTLLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJIANGYUE61610306\u002FFSTLLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJIANGYUE61610306\u002FFSTLLM?color=critical&style=social) | ICML\u003Cbr>2025\n| Traffic | NYC \u003Cbr> CHI \u003Cbr>SIP \u003Cbr>SD | SynEVO | [SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation](https:\u002F\u002Fopenreview.net\u002Fforum?id=Q3rGQUGgWo) | [Code](https:\u002F\u002Fgithub.com\u002FRodger-Lau\u002FSynEVO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRodger-Lau\u002FSynEVO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRodger-Lau\u002FSynEVO?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SEMPO | [SEMPO: Lightweight Foundation Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=YngHXbJM8g) | [Code](https:\u002F\u002Fgithub.com\u002Fmala-lab\u002FSEMPO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmala-lab\u002FSEMPO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmala-lab\u002FSEMPO?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TARFVAE | [TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE](https:\u002F\u002Fopenreview.net\u002Fforum?id=3hnqwOq7iT) | [Code](https:\u002F\u002Fgithub.com\u002FGavine77\u002FTARFVAE) \u003Cbr>! [Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGavine77\u002FTARFVAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGavine77\u002FTARFVAE?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MAFS | [Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation](https:\u002F\u002Fopenreview.net\u002Fforum?id=Uon41HfqR3) | [Code](https:\u002F\u002Fgithub.com\u002Fh505023992\u002FMAFS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fh505023992\u002FMAFS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fh505023992\u002FMAFS?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeXL | [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https:\u002F\u002Fopenreview.net\u002Fforum?id=WRwr2YZ4zt) | None | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DMMV | [Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=PMdHrorFMF) | [Code](https:\u002F\u002Fgithub.com\u002FD2I-Group\u002Fdmmv) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FD2I-Group\u002Fdmmv?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FD2I-Group\u002Fdmmv?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | xLSTM-Mixer | [xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories](https:\u002F\u002Fopenreview.net\u002Fforum?id=JlVn0XRpy0) | [Code](https:\u002F\u002Fgithub.com\u002Fmauricekraus\u002Fxlstm-mixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmauricekraus\u002Fxlstm-mixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmauricekraus\u002Fxlstm-mixer?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TFPS| [Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift](https:\u002F\u002Fopenreview.net\u002Fforum?id=CtoIG9Iwas) | [Code](https:\u002F\u002Fgithub.com\u002FsyrGitHub\u002FTFPS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FsyrGitHub\u002FTFPS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FsyrGitHub\u002FTFPS?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SymTime | [Synthetic Series-Symbol Data Generation for Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=xB1ZNgq0Xp) | [Code](https:\u002F\u002Fgithub.com\u002Fwwhenxuan\u002FSymTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwwhenxuan\u002FSymTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwwhenxuan\u002FSymTime?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | OLinear | [OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain](https:\u002F\u002Fopenreview.net\u002Fforum?id=xB1ZNgq0Xp) | [Code](https:\u002F\u002Fgithub.com\u002Fjackyue1994\u002FOLinear) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjackyue1994\u002FOLinear?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjackyue1994\u002FOLinear?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeEmb | [TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=sLfMvrkn6T) | [Code](https:\u002F\u002Fgithub.com\u002Fshowmeon\u002FTimeEmb) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshowmeon\u002FTimeEmb?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshowmeon\u002FTimeEmb?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-o1 | [Time-o1: Time-Series Forecasting Needs Transformed Label Alignment](https:\u002F\u002Fopenreview.net\u002Fforum?id=RxWILaXuhb) | [Code](https:\u002F\u002Fgithub.com\u002FMaster-PLC\u002FTime-o1) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMaster-PLC\u002FTime-o1?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMaster-PLC\u002FTime-o1?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimePerceiver | [TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=RCeZ063p33) | [Code](https:\u002F\u002Fgithub.comefficient-learning-lab\u002FTimePerceiver) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fefficient-learning-lab\u002FTimePerceiver?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fefficient-learning-lab\u002FTimePerceiver?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MSFT | [Multi-Scale Finetuning for Encoder-based Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=OPOBV0zXu7) | [Code](https:\u002F\u002Fgithub.com\u002Fzqiao11\u002FMSFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzqiao11\u002FMSFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzqiao11\u002FMSFT?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DBLoss | [DBLoss: Decomposition-based Loss Function for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=SbhBIkiRLT) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FDBLoss) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FDBLoss?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FDBLoss?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SRSNet | [Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective](https:\u002F\u002Fopenreview.net\u002Fforum?id=BirE0jYKt0) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FSRSNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FSRSNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FSRSNet?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | IF | [Towards Accurate Time Series Forecasting via Implicit Decoding](https:\u002F\u002Fopenreview.net\u002Fforum?id=gqoeQPhQcE) | [Code](https:\u002F\u002Fgithub.com\u002Frakuyorain\u002FImplicit-Forecaster) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frakuyorain\u002FImplicit-Forecaster?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frakuyorain\u002FImplicit-Forecaster?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat Zero Shot | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TS-RAG | [TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster](https:\u002F\u002Fopenreview.net\u002Fforum?id=PymOnHw4Ty) | [Code](https:\u002F\u002Fgithub.com\u002FUConn-DSIS\u002FTS-RAG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUConn-DSIS\u002FTS-RAG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUConn-DSIS\u002FTS-RAG?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat Traffic| [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | PIR | [Improving Time Series Forecasting via Instance-aware Post-hoc Revision](https:\u002F\u002Fopenreview.net\u002Fforum?id=H7e5RpeIi4) | [Code](https:\u002F\u002Fgithub.com\u002Ficantnamemyself\u002FPIR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ficantnamemyself\u002FPIR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ficantnamemyself\u002FPIR?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat Traffic| Wind \u003Cbr> Temp \u003Cbr> PM25 \u003Cbr> | STELLA | [On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=thHhKPlt8q) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002FSTELLA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002FSTELLA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002FSTELLA?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AliO | [AliO: Output Alignment Matters in Long-Term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=AuOZDp4gy7) | [Code](https:\u002F\u002Fgithub.com\u002Feai-lab\u002FAliO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Feai-lab\u002FAliO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Feai-lab\u002FAliO?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TOTO | [This Time is Different: An Observability Perspective on Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=1jDAYXfcS2) | [Code](https:\u002F\u002Fhuggingface.co\u002FDatadog\u002FToto-Open-Base-1.0) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MoFo| [MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling](https:\u002F\u002Fopenreview.net\u002Fforum?id=sbvLts2HqR) | [Code](https:\u002F\u002Fgithub.com\u002FPoorOtterBob\u002FMoFo) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPoorOtterBob\u002FMoFo?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FPoorOtterBob\u002FMoFo?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning](https:\u002F\u002Fopenreview.net\u002Fforum?id=jy4bBsr1Jc) | [Code](https:\u002F\u002Fgithub.com\u002FSJTU-DMTai\u002FPrune-then-Finetune) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-DMTai\u002FPrune-then-Finetune?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-DMTai\u002FPrune-then-Finetune?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | PIH | [Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Gmwsy7TlFI) | [Code](https:\u002F\u002Fgithub.com\u002Fforever-ly\u002FPIH) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fforever-ly\u002FPIH?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fforever-ly\u002FPIH?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SCAM | [Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=gXOlDLEAjK) | [Code](https:\u002F\u002Fgithub.com\u002FSuDIS-ZJU\u002FSCAM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSuDIS-ZJU\u002FSCAM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSuDIS-ZJU\u002FSCAM?color=critical&style=social) | NIPS\u003Cbr>2025\n| ST SSL | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS07(M) \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | ST-SSDL | [How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=TgGH1bY6kl) | [Code](https:\u002F\u002Fgithub.com\u002FJimmy-7664\u002FST-SSDL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJimmy-7664\u002FST-SSDL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJimmy-7664\u002FST-SSDL?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DecompNet | [DecompNet: Enhancing Time Series Forecasting Models with Implicit Decomposition](https:\u002F\u002Fopenreview.net\u002Fforum?id=ioXn68lBjO) | [Code](https:\u002F\u002Fgithub.com\u002Fluodhhh\u002FDecompNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluodhhh\u002FDecompNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fluodhhh\u002FDecompNet?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr> other | S2TS-LLM | [Bridging Time and Linguistics: LLMs as Time Series Analyzer through Symbolization and Segmentation](https:\u002F\u002Fopenreview.net\u002Fforum?id=nOv6z9RHA5) | [Code](https:\u002F\u002Fgithub.com\u002FJianyangQin\u002FS2TS-LLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJianyangQin\u002FS2TS-LLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJianyangQin\u002FS2TS-LLM?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MSFT | [Multi-Scale Finetuning for Encoder-based Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=OPOBV0zXu7) | [Code](https:\u002F\u002Fgithub.com\u002Fzqiao11\u002FMSFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzqiao11\u002FMSFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzqiao11\u002FMSFT?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AMRC | [Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency](https:\u002F\u002Fopenreview.net\u002Fforum?id=KrglRiOKYT) | [Code](https:\u002F\u002Fgithub.com\u002FMazelTovy\u002FAMRC) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMazelTovy\u002FAMRC?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMazelTovy\u002FAMRC?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SL | [Selective Learning for Deep Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=kgzRy6nD6D) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002Fselective-learning) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002Fselective-learning?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002Fselective-learning?color=critical&style=social) | NIPS\u003Cbr>2025\n| Evolve Traffic | Air-Str\u003Cbr> PEMS-Str \u003Cbr> Energy-Str | EAC | [Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=FRzCIlkM7I) | [Code](https:\u002F\u002Fgithub.com\u002FOnedean\u002FEAC) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FOnedean\u002FEAC?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FOnedean\u002FEAC?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeMixer++ | [TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https:\u002F\u002Fopenreview.net\u002Fforum?id=1CLzLXSFNn) | [Code](https:\u002F\u002Fgithub.com\u002Fkwuking\u002FTimeMixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkwuking\u002FTimeMixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkwuking\u002FTimeMixer?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-MoE | [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https:\u002F\u002Fopenreview.net\u002Fforum?id=e1wDDFmlVu) | [Code](https:\u002F\u002Fgithub.com\u002FTime-MoE\u002FTime-MoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TVNet | [TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation](https:\u002F\u002Fopenreview.net\u002Fforum?id=MZDdTzN6Cy) | [Code](https:\u002F\u002Fgithub.com\u002FTime-MoE\u002FTime-MoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeKAN | [TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=wTLc79YNbh) | [Code](https:\u002F\u002Fgithub.com\u002Fhuangst21\u002FTimeKAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuangst21\u002FTimeKAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuangst21\u002FTimeKAN?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | ICTSP | [In-context Time Series Predictor](https:\u002F\u002Fopenreview.net\u002Fforum?id=dCcY2pyNIO) | [Code](https:\u002F\u002Fgithub.com\u002FLJC-FVNR\u002FIn-context-Time-Series-Predictor) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLJC-FVNR\u002FIn-context-Time-Series-Predictor?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLJC-FVNR\u002FIn-context-Time-Series-Predictor?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FSCA | Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=syC2764fPc) | [Code](https:\u002F\u002Fgithub.com\u002Ftokaka22\u002FICLR25-FSCA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftokaka22\u002FICLR25-FSCA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftokaka22\u002FICLR25-FSCA?color=critical&style=social) | ICLR\u003Cbr>2025\n|Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SimpleTM | SimpleTM: A Simple Baseline for Multivariate Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=oANkBaVci5) | [Code](https:\u002F\u002Fgithub.com\u002Fvsingh-group\u002FSimpleTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvsingh-group\u002FSimpleTM-FSCA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvsingh-group\u002FSimpleTM?color=critical&style=social) | ICLR\u003Cbr>2025\n|Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | Towards Neural Scaling Laws for Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=uCqxDfLYrB) | [Code](https:\u002F\u002Fgithub.com\u002FQingrenn\u002FTSFM-ScalingLaws) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FQingrenn\u002FTSFM-ScalingLaws?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FQingrenn\u002FTSFM-ScalingLaws?color=critical&style=social) | ICLR\u003Cbr>2025 \n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Timer-XL | [Timer-XL: Long-Context Transformers for Unified Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=KMCJXjlDDr) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTimer-XL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FTimer-XL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FTimer-XL?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LCESN | [Locally Connected Echo State Networks for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=KeRwLLwZaw) | [Code](https:\u002F\u002Fgithub.com\u002FFloopCZ\u002Fecho-state-networks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFloopCZ\u002Fecho-state-networks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFloopCZ\u002Fecho-state-networks?color=critical&style=social) | ICLR\u003Cbr>2025\n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> ... | AutoSTF | [AutoSTF: Decoupled Neural Architecture Search for Cost-Effective Automated Spatio-Temporal Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709323) | [Code](https:\u002F\u002Fgithub.com\u002Fusail-hkust\u002FAutoSTF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fusail-hkust\u002FAutoSTF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fusail-hkust\u002FAutoSTF?color=critical&style=social) | KDD\u003Cbr>2025\n| Traffic | LargeST | PatchSTG | [Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709177) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FPatchSTG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FPatchSTG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FPatchSTG?color=critical&style=social) | KDD\u003Cbr>2025\n| Traffic | CHITaxi \u003Cbr> CHIBike \u003Cbr> WSHBike \u003Cbr> NYBike | ProST | [ProST: Prompt Future Snapshot on Dynamic Graphs for Spatio-Temporal Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709273) | None | KDD\u003Cbr>2025\n| Traffic \u003Cbr> unseen| NYCTaxi \u003Cbr> NYCBike \u003Cbr> BJTaxi | STEVE | [Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709201) | [Code](https:\u002F\u002Fgithub.com\u002Fbigscity\u002FSTEVE_CODE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbigscity\u002FSTEVE_CODE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbigscity\u002FSTEVE_CODE?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DUET | [DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709325) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FDUET) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FDUET?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FDUET?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TSFM-Bench | [TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737442) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FTSFM-Bench) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FTSFM-Bench?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FTSFM-Bench?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | QuantumTime | [Quantum Time-index Models with Reservoir for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709228) | [Code](https:\u002F\u002Fgithub.com\u002FQuaRobot\u002FQuantumTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FQuaRobot\u002FQuantumTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FQuaRobot\u002FQuantumTime?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | ST-MTM | [ST-MTM: Masked Time Series Modeling with Seasonal-Trend Decomposition for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709254) | [Code](https:\u002F\u002Fgithub.com\u002Fhwseo95\u002Fst-mtm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhwseo95\u002Fst-mtm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhwseo95\u002Fst-mtm?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CMA | [CMA: A Unified Contextual Meta-Adaptation Methodology for Time-Series Denoising and Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3711896.3736881) | [Code](https:\u002F\u002Fgithub.com\u002FFancyAI-SCNU\u002FCMA_KDD_2025) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFancyAI-SCNU\u002FCMA_KDD_2025?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFancyAI-SCNU\u002FCMA_KDD_2025?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CrossLinear | [CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736899) | [Code](https:\u002F\u002Fgithub.com\u002Fmumiao2000\u002FCrossLinear) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmumiao2000\u002FCrossLinear?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmumiao2000\u002FCrossLinear?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BLAST | [BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736860) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002FBLAST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002FBLAST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002FBLAST?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeCapsule | [TimeCapsule: Solving the Jigsaw Puzzle of Long-Term Time Series Forecasting with Compressed Predictive Representations](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737157) | [Code](https:\u002F\u002Fgithub.com\u002FLuoauoa\u002FTimeCapsule) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLuoauoa\u002FTimeCapsule?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLuoauoa\u002FTimeCapsule?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MoA | [Semantics-Aware Patch Encoding and Hierarchical Dependency Modeling for Long-Term Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737123) | [Code](https:\u002F\u002Fgithub.com\u002Flunaaa95\u002Fmou) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flunaaa95\u002Fmou?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flunaaa95\u002Fmou?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SDE | [SDE: A Simplified and Disentangled Dependency Encoding Framework for State Space Models in Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737119) | [Code](https:\u002F\u002Fgithub.com\u002FYukinoAsuna\u002FSAMBA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYukinoAsuna\u002FSAMBA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYukinoAsuna\u002FSAMBA?color=critical&style=social) | KDD\u003Cbr>2025\n| Traffic | BIKE \u003Cbr> PEMS03 \u003Cbr> BJ500 \u003Cbr> METR-LA | STH-SepNet | [Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736904) | [Code](https:\u002F\u002Fgithub.com\u002Fjiawenchen10\u002FSTHSepNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjiawenchen10\u002FSTHSepNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjiawenchen10\u002FSTHSepNet?color=critical&style=social) | KDD\u003Cbr>2025\n| Evolve Traffic | Electricity \u003Cbr> PeMS \u003Cbr> Weather | STEV | [Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736854) | None | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SoP | [Non-collective Calibrating Strategy for Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2025\u002F0371) | [Code](https:\u002F\u002Fgithub.com\u002Fhanyuki23\u002FSoP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhanyuki23\u002FSoP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhanyuki23\u002FSoP?color=critical&style=social) | IJCAI\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | VisMoE | [Seeing Sequences like Humans: Pattern Classification Driven Time-Series Forecasting via Vision Language Models](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761199) | [Code](https:\u002F\u002Fgithub.com\u002FLiu905169\u002FVisMoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiu905169\u002FVisMoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiu905169\u002FVisMoE?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BIM3 | [Bidirectional Temporal-Aware Modeling with Multi-Scale Mixture-of-Experts for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761273) | [Code](https:\u002F\u002Fgithub.com\u002Fyifan-gao-dev\u002FBIM3) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyifan-gao-dev\u002FBIM3?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyifan-gao-dev\u002FBIM3?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BALM-TS | [BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761278) | [Code](https:\u002F\u002Fgithub.com\u002FShiqiaoZhou\u002FBALM-TSF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FShiqiaoZhou\u002FBALM-TSF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FShiqiaoZhou\u002FBALM-TSF?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AdaPatch | [AdaPatch: Adaptive Patch-Level Modeling for Non-Stationary Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761360) | [Code](https:\u002F\u002Fgithub.com\u002Fiuaku\u002FAdaPatch) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fiuaku\u002FAdaPatch?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fiuaku\u002FAdaPatch?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | WDformer | [WDformer: A Wavelet-based Differential Transformer Model for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761348) | [Code](https:\u002F\u002Fgithub.com\u002Fxiaowangbc\u002FWDformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxiaowangbc\u002FWDformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxiaowangbc\u002FWDformer?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | HRCformer | [HRCformer: Hierarchical Recursive Convolution-Transformer with Multi-Scale Adaptive Recalibration for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761308) | None | CIKM\u003Cbr>2025\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> China-AQI \u003Cbr> Electricity \u003Cbr> Solar \u003Cbr> Temperature | ST-Hyper | [ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761281) | None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | EAPformer | [Bidirectional Temporal-Aware Modeling with Multi-Scale Mixture-of-Experts for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761055) | [Code](https:\u002F\u002Fgithub.com\u002FIvER1234689\u002FMultivariate-Long-Term-Time-Series-Forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FIvER1234689\u002FMultivariate-Long-Term-Time-Series-Forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FIvER1234689\u002FMultivariate-Long-Term-Time-Series-Forecasting?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MillGNN | [MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761173) | None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MSOFormer | [MSOFormer: Multi-scale Transformer with Orthogonal Embedding and Frequency Modeling for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761143) | None | CIKM\u003Cbr>2025\n| Zero Shot | Parking \u003Cbr> [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DANet | [DANet: A RAG-inspired Dual Attention Model for Few-shot Time Series Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761012) | None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Structural Entropy-based Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761007) | None| CIKM\u003Cbr>2025\n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | TopKNet | [TopKNet:Learning to Perceive the Top-K Pivotal Nodes in Spatio-Temporal Data for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3760993) | [Code](https:\u002F\u002Fgithub.com\u002Frandomforest1111\u002FTopKNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frandomforest1111\u002FTopKNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frandomforest1111\u002FTopKNet?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | NYCTaxi \u003Cbr> CityBike \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | ST-LINK | [ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761085) | [Code](https:\u002F\u002Fgithub.com\u002FHyoTaek98\u002FST_LINK) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHyoTaek98\u002FST_LINK?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHyoTaek98\u002FST_LINK?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic \u003Cbr> Random Missing | PEMS04 \u003Cbr> PEMS08 | STMMoE | [Spatio-Temporal Forecasting under Open-World Missingness with Adaptive Mixture-of-Experts](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761403) | [Code](https:\u002F\u002Fgithub.com\u002Fchenywu\u002FSTMMoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenywu\u002FSTMMoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenywu\u002FSTMMoE?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic \u003Cbr> Node Missing | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> ... | STA-GANN | [STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761045) | [Code](https:\u002F\u002Fgithub.com\u002Fblisky-li\u002FSTAGANN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fblisky-li\u002FSTAGANN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fblisky-li\u002FSTAGANN?color=critical&style=social) | CIKM\u003Cbr>2025\n| Finance | Crypto \u003Cbr> Forex \u003Cbr> Future\u003Cbr> Stock\u003Cbr> Econ\u003Cbr> Others | FinCast | [FinCast: A Foundation Model for Financial Time-Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761261) | [Code](https:\u002F\u002Fgithub.com\u002Fvincent05r\u002FFinCast-fts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvincent05r\u002FFinCast-fts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvincent05r\u002FFinCast-fts?color=critical&style=social) | CIKM\u003Cbr>2025\n| Wind Power | China \u003Cbr> Texas | | [Multivariate Wind Power Time Series Forecasting with Noise-Filtering Neural ODEs](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761118) | None| CIKM\u003Cbr>2025\n| Traffic | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> CHIBike | DSformer | [Extracting Global Temporal Patterns Within Short Look-Back Windows for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761212) | [Code](https:\u002F\u002Fgithub.com\u002Fsky836\u002FDSFormer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsky836\u002FDSFormer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsky836\u002FDSFormer?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DoP | [Decoder-only Pre-training Enhancement for Spatio-temporal Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761432) | [Code](https:\u002F\u002Fgithub.com\u002Fhikvision-research\u002FDoP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhikvision-research\u002FDoP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhikvision-research\u002FDoP?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | PEMS07(M) \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> NYCTaxi \u003Cbr> NYCBike | SSMOE | [Mixture of Semantic and Spatial Experts for Explainable Traffic Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761412) | None | CIKM\u003Cbr>2025\n| Traffic | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | MultiGran | [Forecasting at Full Spectrum: Holistic Multi-Granular Traffic Modeling under High-Throughput Inference Regimes](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761330) | None | CIKM\u003Cbr>2025\n| Traffic | I-80 \u003Cbr> US-101 \u003Cbr> Complex-\u003Cbr>highway | TPN | [Balance and Brighten: A Twin-Propeller Network to Release Potential of Physics Laws for Traffic State Estimation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761207) | [Code](https:\u002F\u002Fgithub.com\u002Fxxxabc01\u002FTPN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxxxabc01\u002FTPN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxxxabc01\u002FTPN?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr>Jinan | FEDDGCN | [FEDDGCN: A Frequency-Enhanced Decoupling Dynamic Graph Convolutional Network for Traffic Flow Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761048) |None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SSCNN | [Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2024\u002Fhash\u002F7b122d0a0dcb1a86ffa25ccba154652b-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FSSCNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJLDeng\u002FSSCNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJLDeng\u002FSSCNN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Are Language Models Actually Useful for Time Series Forecasting?](https:\u002F\u002Fopenreview.net\u002Fforum?id=54NSHO0lFe) | [Code](https:\u002F\u002Fgithub.com\u002FBennyTMT\u002FLLMsForTimeSeries) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBennyTMT\u002FLLMsForTimeSeries?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBennyTMT\u002FLLMsForTimeSeries?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | PGN | [PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=ypEamFKu2O¬eId=jpzTU4OIxe) | [Code](https:\u002F\u002Fgithub.com\u002FWater2sea\u002FTPGN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWater2sea\u002FTPGN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWater2sea\u002FTPGN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CATS | [Are Self-Attentions Effective for Time Series Forecasting?](https:\u002F\u002Fopenreview.net\u002Fforum?id=iN43sJoib7¬eId=VrwF0T4VGH) | [Code](https:\u002F\u002Fgithub.com\u002Fdongbeank\u002FCATS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdongbeank\u002FCATS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdongbeank\u002FCATS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Attraos | [Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective](https:\u002F\u002Fopenreview.net\u002Fforum?id=fEYHZzN7kX) | [Code](https:\u002F\u002Fgithub.com\u002FCityMind-Lab\u002FNeurIPS24-Attraos) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCityMind-Lab\u002FNeurIPS24-Attraos?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCityMind-Lab\u002FNeurIPS24-Attraos?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-FFM | [Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=HS0faHRhWD) | [Code](https:\u002F\u002Fgithub.com\u002Fyuppielqx\u002FTime-FFM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuppielqx\u002FTime-FFM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuppielqx\u002FTime-FFM?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Chimera | [Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=ncYGjx2vnE) | [Code](https:\u002F\u002Fgithub.com\u002FABehrouz\u002FChimera) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FABehrouz\u002FChimera?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FABehrouz\u002FChimera?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeXer | [TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables](https:\u002F\u002Fopenreview.net\u002Fforum?id=INAeUQ04lT) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTimeXer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FTimeXer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FTimeXer?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MiTSformer| [Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment](https:\u002F\u002Fopenreview.net\u002Fforum?id=EMV8nIDZJn) | [Code](https:\u002F\u002Fgithub.com\u002Fchunhuiz\u002FMiTSformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchunhuiz\u002FMiTSformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchunhuiz\u002FMiTSformer?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TTMs| [Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero\u002FFew-Shot Forecasting of Multivariate Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=3O5YCEWETq) | [Code](https:\u002F\u002Fgithub.com\u002Fibm-granite\u002Fgranite-tsfm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fibm-granite\u002Fgranite-tsfm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fibm-granite\u002Fgranite-tsfm?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Sumba| [Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics](https:\u002F\u002Fopenreview.net\u002Fforum?id=co7DsOwcop) | [Code](https:\u002F\u002Fgithub.com\u002Fchenxiaodanhit\u002FSumba) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenxiaodanhit\u002FSumba?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenxiaodanhit\u002FSumba?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Peri-midF | [Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis](https:\u002F\u002Fopenreview.net\u002Fforum?id=5iUxMVJVEV) | [Code](https:\u002F\u002Fgithub.com\u002FWuQiangXDU\u002FPeri-midFormer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWuQiangXDU\u002FPeri-midFormer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWuQiangXDU\u002FPeri-midFormer?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Ada-MSHyper | [Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=RNbrIQ0se8) | [Code](https:\u002F\u002Fgithub.com\u002Fshangzongjiang\u002FAda-MSHyper) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshangzongjiang\u002FAda-MSHyper?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshangzongjiang\u002FAda-MSHyper?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | ... | LPTM | [Large Pre-trained time series models for cross-domain Time series analysis tasks](https:\u002F\u002Fopenreview.net\u002Fforum?id=vMMzjCr5Zj) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FLPTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FLPTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FLPTM?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CCM | [From Similarity to Superiority: Channel Clustering for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=MDgn9aazo0) | [Code](https:\u002F\u002Fgithub.com\u002FGraph-and-Geometric-Learning\u002FTimeSeriesCCM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-and-Geometric-Learning\u002FTimeSeriesCCM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-and-Geometric-Learning\u002FTimeSeriesCCM?color=critical&style=social) | NIPS\u003Cbr>2024\n| Add News | Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Bitcoin | | [From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection](https:\u002F\u002Fopenreview.net\u002Fforum?id=DpByqSbdhI) | [Code](https:\u002F\u002Fgithub.com\u002Fameliawong1996\u002FFrom_News_to_Forecast) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fameliawong1996\u002FFrom_News_to_Forecast?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fameliawong1996\u002FFrom_News_to_Forecast?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | ImageBind \u003Cbr> IMU2CLIP \u003Cbr> IMUGPT \u003Cbr> HARGPT \u003Cbr> LLaVA | UniMTS | [UniMTS: Unified Pre-training for Motion Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=DpByqSbdhI) | [Code](https:\u002F\u002Fgithub.com\u002Fxiyuanzh\u002FUniMTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxiyuanzh\u002FUniMTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxiyuanzh\u002FUniMTS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Attack | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> Weather \u003Cbr> ETTm1 | BackTime | [BackTime: Backdoor Attacks on Multivariate Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=y8HUXkwAOg) | [Code](https:\u002F\u002Fgithub.com\u002Fxiaolin-cs\u002FBackTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxiaolin-cs\u002FBackTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxiaolin-cs\u002FBackTime?color=critical&style=social) | NIPS\u003Cbr>2024\n| Less data | Electricity \u003Cbr> Solar \u003Cbr> Traffic \u003Cbr> PEMS-BAY \u003Cbr> METR-LA | ChronoEpilogi | [ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions](https:\u002F\u002Fopenreview.net\u002Fforum?id=y8HUXkwAOg) | [Code](https:\u002F\u002Fgithub.com\u002Fev07\u002FChronoEpilogi) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fev07\u002FChronoEpilogi?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fev07\u002FChronoEpilogi?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FAN | [Frequency Adaptive Normalization For Non-stationary Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=T0axIflVDD) | [Code](https:\u002F\u002Fgithub.com\u002Fwayne155\u002FFAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwayne155\u002FFAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwayne155\u002FFAN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | GLAFF | [Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective](https:\u002F\u002Fopenreview.net\u002Fforum?id=EY2agT920S) | [Code](https:\u002F\u002Fgithub.com\u002FForestsKing\u002FGLAFF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FForestsKing\u002FGLAFF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FForestsKing\u002FGLAFF?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FilterNet | [FilterNet: Harnessing Frequency Filters for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=ugL2D9idAD) | [Code](https:\u002F\u002Fgithub.com\u002Faikunyi\u002FFilterNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faikunyi\u002FFilterNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faikunyi\u002FFilterNet?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CycleNet | [CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns](https:\u002F\u002Fopenreview.net\u002Fforum?id=clBiQUgj4w) | [Code](https:\u002F\u002Fgithub.com\u002FACAT-SCUT\u002FCycleNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FACAT-SCUT\u002FCycleNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FACAT-SCUT\u002FCycleNet?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | RATD | [Retrieval-Augmented Diffusion Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=dRJJt0Ji48¬eId=8wGyyvVUNr) | [Code](https:\u002F\u002Fgithub.com\u002Fstanliu96\u002FRATD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fstanliu96\u002FRATD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fstanliu96\u002FRATD?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DDN | [DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=RVZfra6sZo) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FDDN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FDDN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FDDN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FBM | [Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=BAfKBkr8IP) | [Code](https:\u002F\u002Fgithub.com\u002Frunze1223\u002FFourier-Basis-Mapping) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frunze1223\u002FFourier-Basis-Mapping?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frunze1223\u002FFourier-Basis-Mapping?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BSA | [Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=dxyNVEBQMp) | [Code](https:\u002F\u002Fgithub.com\u002FDJLee1208\u002FBSA_2024) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDJLee1208\u002FBSA_2024?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDJLee1208\u002FBSA_2024?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DeformableTST | [DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching](https:\u002F\u002Fopenreview.net\u002Fforum?id=B1Iq1EOiVU) | [Code](https:\u002F\u002Fgithub.com\u002Fluodhhh\u002FDeformableTST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluodhhh\u002FDeformableTST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fluodhhh\u002FDeformableTST?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SOFTS | [SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion](https:\u002F\u002Fopenreview.net\u002Fforum?id=89AUi5L1uA) | [Code](https:\u002F\u002Fgithub.com\u002FSecilia-Cxy\u002FSOFTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSecilia-Cxy\u002FSOFTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSecilia-Cxy\u002FSOFTS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Scaling Law for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Cr2jEHJB9q) | [Code](https:\u002F\u002Fgithub.com\u002FJingzheShi\u002FScalingLawForTimeSeriesForecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJingzheShi\u002FScalingLawForTimeSeriesForecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJingzheShi\u002FScalingLawForTimeSeriesForecasting?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AutoTimes | [AutoTimes: Autoregressive Time Series Forecasters via Large Language Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=HS0faHRhWD) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FAutoTimes) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FAutoTimes?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FAutoTimes?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multi Task | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | UniTS | [UniTS: A Unified Multi-Task Time Series Model](https:\u002F\u002Fopenreview.net\u002Fforum?id=nBOdYBptWW) | [Code](https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FUniTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmims-harvard\u002FUniTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmims-harvard\u002FUniTS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Foundation TS | ... | MOMENT | [MOMENT: A Family of Open Time-series Foundation Models](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F34530) | [Code](https:\u002F\u002Fgithub.com\u002Fmoment-timeseries-foundation-model\u002Fmoment) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmoment-timeseries-foundation-model\u002Fmoment?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmoment-timeseries-foundation-model\u002Fmoment?color=critical&style=social) | ICML\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | OSL | [An Analysis of Linear Time Series Forecasting Models](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F32697) | [Code](https:\u002F\u002Fgithub.com\u002Fsir-lab\u002Flinear-forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsir-lab\u002Flinear-forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsir-lab\u002Flinear-forecasting?color=critical&style=social) | ICML\u003Cbr>2024\n| Six | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | UP2ME | [UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F33686) | [Code](https:\u002F\u002Fgithub.com\u002FThinklab-SJTU\u002FUP2ME) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FThinklab-SJTU\u002FUP2ME?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FThinklab-SJTU\u002FUP2ME?color=critical&style=social) | ICML\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SparseTSF | [SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters](https:\u002F\u002Fopenreview.net\u002Fforum?id=54NSHO0lFe) | [Code](https:\u002F\u002Fgithub.com\u002Flss-1138\u002FSparseTSF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flss-1138\u002FSparseTSF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flss-1138\u002FSparseTSF?color=critical&style=social) | ICML\u003Cbr>2024\n| Multivariat | Electricity \u003Cbr> PEMSD7M \u003Cbr> BikeNYC \u003Cbr> [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SCNN | [Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10457027) | [Code](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FSCNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJLDeng\u002FSCNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJLDeng\u002FSCNN?color=critical&style=social) | TKDE \u003Cbr> 2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | iTransformer | [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=JePfAI8fah) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FiTransformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FiTransformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FiTransformer?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | NorPool \u003Cbr> Caiso \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Exchange \u003Cbr> ETT \u003Cbr> Wind | mr-Diff | [Multi-Resolution Diffusion Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=mmjnr0G8ZY) | None | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Traffic \u003Cbr> Exchange \u003Cbr> ILI | ModernTCN | [Multi-Resolution Diffusion Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU) | [Code](https:\u002F\u002Fgithub.com\u002Fluodhhh\u002FModernTCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluodhhh\u002FModernTCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fluodhhh\u002FModernTCN?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-LLM | [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=Unb5CVPtae) | [Code](https:\u002F\u002Fgithub.com\u002FKimMeen\u002FTime-LLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKimMeen\u002FTime-LLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKimMeen\u002FTime-LLM?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TEMPO | [TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=YH5w12OUuU) | [Code](https:\u002F\u002Fgithub.com\u002FDC-research\u002FTEMPO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDC-research\u002FTEMPO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDC-research\u002FTEMPO?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CARD | [CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=MJksrOhurE) | [Code](https:\u002F\u002Fgithub.com\u002Fwxie9\u002FCARD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwxie9\u002FCARD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwxie9\u002FCARD?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | ARM | [ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=JWpwDdVbaM) | None | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DAM | [DAM: Towards a Foundation Model for Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=4NhMhElWqP) | [None](https:\u002F\u002Fopenreview.net\u002Fattachment?id=4NhMhElWqP&name=supplementary_material) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr> PEMS3478 | TimeMixer | [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=7oLshfEIC2) | [Code](https:\u002F\u002Fgithub.com\u002Fkwuking\u002FTimeMixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkwuking\u002FTimeMixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkwuking\u002FTimeMixer?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | PDF | [Periodicity Decoupling Framework for Long-term Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=dp27P5HBBt) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FPDF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FPDF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FPDF?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat \u003Cbr> Missing Value| METR-LA \u003Cbr> Electricity \u003Cbr> PEMS \u003Cbr> ETT \u003Cbr> BeijingAir| BiTGraph | [Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values](https:\u002F\u002Fopenreview.net\u002Fforum?id=O9nZCwdGcG) | [Code](https:\u002F\u002Fgithub.com\u002Fchenxiaodanhit\u002FBiTGraph) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenxiaodanhit\u002FBiTGraph?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenxiaodanhit\u002FBiTGraph?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr> PEMS08 | LIFT | [Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators](https:\u002F\u002Fopenreview.net\u002Fforum?id=JiTVtCUOpS) | [Code](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FLIFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FLIFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FLIFT?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Traffic | STanHop | [STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=6iwg437CZs) | [Code](https:\u002F\u002Fgithub.com\u002FMAGICS-LAB\u002FSTanHop) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMAGICS-LAB\u002FSTanHop?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMAGICS-LAB\u002FSTanHop?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> ILI \u003Cbr> CloudCluster | Pathformer | [Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002Fpathformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002Fpathformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002Fpathformer?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | pits | [Learning to Embed Time Series Patches Independently](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU) | [Code](https:\u002F\u002Fgithub.com\u002Fseunghan96\u002Fpits) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseunghan96\u002Fpits?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fseunghan96\u002Fpits?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic | FITS | [FITS: Modeling Time Series with 10k Parameters](https:\u002F\u002Fopenreview.net\u002Fforum?id=bWcnvZ3qMb) | [Code](https:\u002F\u002Fgithub.com\u002FVEWOXIC\u002FFITS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVEWOXIC\u002FFITS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVEWOXIC\u002FFITS?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Lora | AutoTCL | [Parametric Augmentation for Time Series Contrastive Learnin](https:\u002F\u002Fopenreview.net\u002Fforum?id=EIPLdFy3vp) | [Code](https:\u002F\u002Fgithub.com\u002FAslanDing\u002FAutoTCL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAslanDing\u002FAutoTCL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAslanDing\u002FAutoTCL?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Exchange \u003Cbr> ILI | GLIP | [Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=aFWUY3E7ws) | [Code](https:\u002F\u002Fopenreview.net\u002Fattachment?id=aFWUY3E7ws&name=supplementary_material) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Fredformer | [Fredformer: Frequency Debiased Transformer for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671855) | [Code](https:\u002F\u002Fgithub.com\u002FchenzRG\u002FFredformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FchenzRG\u002FFredformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FchenzRG\u002FFredformer?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | GPHT | [Generative Pretrained Hierarchical Transformer for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671855) | [Code](https:\u002F\u002Fgithub.com\u002Ficantnamemyself\u002FGPHT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ficantnamemyself\u002FGPHT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ficantnamemyself\u002FGPHT?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FRNet | [FRNet: Frequency-based Rotation Network for Long-term Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671713) | [Code](https:\u002F\u002Fgithub.com\u002FSiriZhang45\u002FFRNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSiriZhang45\u002FFRNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSiriZhang45\u002FFRNet?color=critical&style=social) | KDD\u003Cbr>2024\n| Missing \u003Cbr> MTS | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> China AQI | GinAR | [GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3672055) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002FGinAR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002FGinAR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002FGinAR?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | HimNet | [Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671961) | [Code](https:\u002F\u002Fgithub.com\u002FXDZhelheim\u002FHimNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FXDZhelheim\u002FHimNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FXDZhelheim\u002FHimNet?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CDS | [Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671926) | [Code](https:\u002F\u002Fgithub.com\u002FHALF111\u002Fcalibration_CDS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHALF111\u002Fcalibration_CDS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHALF111\u002Fcalibration_CDS?color=critical&style=social) | KDD\u003Cbr>2024\n| Foundation \u003Cbr> Traffic | TaxiBJ \u003Cbr> Crawd \u003Cbr> BikeNYC \u003Cbr> Cellular \u003Cbr> TDrive \u003Cbr> TrafficSH | UniST | [UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671662) | [Code](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FUniST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FUniST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FUniST?color=critical&style=social) | KDD\u003Cbr>2024\n| Early \u003Cbr> Traffic | METR-LA \u003Cbr> EMS \u003Cbr> NYPD | STEMO | [STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671922) | [Code](https:\u002F\u002Fgithub.com\u002Fcoco0106\u002FMO-STEP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcoco0106\u002FMO-STEP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcoco0106\u002FMO-STEP?color=critical&style=social) | KDD\u003Cbr>2024\n| New nodes \u003Cbr> Traffic | Large-ST | STONE | [STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671680) | [Code](https:\u002F\u002Fgithub.com\u002FPoorOtterBob\u002FSTONE-KDD-2024) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPoorOtterBob\u002FSTONE-KDD-2024?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FPoorOtterBob\u002FSTONE-KDD-2024?color=critical&style=social) | KDD\u003Cbr>2024\n| Irregular \u003Cbr> Traffic | Zhuzhou \u003Cbr> Baoding | Aseer | [Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671665) | [Code](https:\u002F\u002Fgithub.com\u002Fusail-hkust\u002FASeer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fusail-hkust\u002FASeer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fusail-hkust\u002FASeer?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | Stock \u003Cbr> Exchange \u003Cbr> Weather | CONTIME | [Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671969) | [Code](https:\u002F\u002Fgithub.com\u002Fsheoyon-jhin\u002FCONTIME) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsheoyon-jhin\u002FCONTIME?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsheoyon-jhin\u002FCONTIME?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | PEMS07 \u003Cbr> Large-ST | GWT | [Pre-Training Identification of Graph Winning Tickets in Adaptive Spatial-Temporal Graph Neural Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671912) | [Code](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002Fpaper-1430) | KDD\u003Cbr>2024\n| Large Scale | Large-ST | RPMixer | [RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671881) | [Code](https:\u002F\u002Fsites.google.com\u002Fview\u002Frpmixer) | KDD\u003Cbr>2024\n| Demand Supply \u003Cbr> Prediction | Shanghai \u003Cbr> Zhengzhou | MulSTE | [MulSTE: A Multi-view Spatio-temporal Learning Framework with Heterogeneous Event Fusion for Demand-supply Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3672030) | [Code](https:\u002F\u002Fgithub.com\u002Fmulste-kdd2024\u002FMulSTE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmulste-kdd2024\u002FMulSTE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmulste-kdd2024\u002FMulSTE?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | 108s | AutoXPCR | [AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3672057) | [TF](https:\u002F\u002Fgithub.com\u002Fraphischer\u002Fxpcr) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fraphischer\u002Fxpcr?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fraphischer\u002Fxpcr?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | UniTime | [UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3589334.3645434) | [Code](https:\u002F\u002Fgithub.com\u002Fliuxu77\u002FUniTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliuxu77\u002FUniTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliuxu77\u002FUniTime?color=critical&style=social) | WWW 2024\n| Multivariat | Ross \u003Cbr> Saratoga \u003Cbr> UpperPen \u003Cbr> SFC | DAN | [Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F27768) | [Code](https:\u002F\u002Fgithub.com\u002Fdavidanastasiu\u002Fdan) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdavidanastasiu\u002Fdan?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdavidanastasiu\u002Fdan?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | ILI \u003Cbr> Weather \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> ETT \u003Cbr> Exchange | HDMixer | [HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29155) | [Code](https:\u002F\u002Fgithub.com\u002Fhqh0728\u002FHDMixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhqh0728\u002FHDMixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhqh0728\u002FHDMixer?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> England \u003Cbr> TaxiBJ \u003Cbr> PEMS-BAY | STPGNN | [Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28707) | None | AAAI\u003Cbr>2024\n| Multivariat | FD001 \u003Cbr> FD002 \u003Cbr> FD003 \u003Cbr> FD004 | FC-STGNN | [Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29500) | [Code](https:\u002F\u002Fgithub.com\u002FFrank-Wang-oss\u002FFCSTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFrank-Wang-oss\u002FFCSTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFrank-Wang-oss\u002FFCSTGNN?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | PEMS04 \u003Cbr> PEMS08 \u003Cbr> blockchain | TMP-Nets | [Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29051) | None | AAAI\u003Cbr>2024\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY | ModWaveMLP | [ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28753) | [TF](https:\u002F\u002Fgithub.com\u002FKqingzheng\u002FModWaveMLP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKqingzheng\u002FModWaveMLP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKqingzheng\u002FModWaveMLP?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat |Flight \u003Cbr> Weather \u003Cbr> ETT \u003Cbr> Electricity \u003Cbr> Exchange | MSGNet | [MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28991) | [Code](https:\u002F\u002Fgithub.com\u002FYoZhibo\u002FMSGNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYoZhibo\u002FMSGNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYoZhibo\u002FMSGNet?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | Self-PeMS | DLF | [Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28759) | [Code](https:\u002F\u002Fgithub.com\u002Fwangbinwu13116175205\u002FDLF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwangbinwu13116175205\u002FDLF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwangbinwu13116175205\u002FDLF?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat |ETT \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Exchange | HTV-Trans | [Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29483) | [Code](https:\u002F\u002Fgithub.com\u002Fflare200020\u002FHTV_Trans) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fflare200020\u002FHTV_Trans?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fflare200020\u002FHTV_Trans?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat |A-share \u003Cbr> Cross-Market \u003Cbr> ETT | ST-DAN| [Adaptive Meta-Learning Probabilistic Inference Framework for Long Sequence Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29661) | [Code](https:\u002F\u002Fgithub.com\u002FZhu-JP\u002FAMPIF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhu-JP\u002FAMPIF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZhu-JP\u002FAMPIF?color=critical&style=social) | AAAI\u003Cbr>2024\n| Six | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CTRL | [An NCDE-based Framework for Universal Representation Learning of Time Series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F511) | [Code](https:\u002F\u002Fgithub.com\u002FLiuZH-19\u002FCTRL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiuZH-19\u002FCTRL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiuZH-19\u002FCTRL?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic | PEMS3478 | STD-MAE | [Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F442) | [Code](https:\u002F\u002Fgithub.com\u002FJimmy-7664\u002FSTD-MAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJimmy-7664\u002FSTD-MAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJimmy-7664\u002FSTD-MAE?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DERITS | [Deep Frequency Derivative Learning for Non-stationary Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F436) | None | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Skip-Timef | [Skip-Timeformer: Skip-Time Interaction Transformer for Long Sequence Time-Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F608) | None | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | VCformer | [VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F590) | [Code](https:\u002F\u002Fgithub.com\u002FCSyyn\u002FVCformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCSyyn\u002FVCformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCSyyn\u002FVCformer?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LeRet | [LeRet: Language-Empowered Retentive Network for Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F460) | [Code](https:\u002F\u002Fgithub.com\u002Fhqh0728\u002FLeRet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhqh0728\u002FLeRet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhqh0728\u002FLeRet?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Missing Variate | METR-LA \u003Cbr> Solar \u003Cbr> Traffic \u003Cbr> ECG5000 | SDformer | [SDformer: Transformer with Spectral Filter and Dynamic Attention for Multivariate Time Series Long-term Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F228) | None | IJCAI\u003Cbr>2024\n| Traffic | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMSD7M | DCST | [Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F288) | [Code](https:\u002F\u002Fgithub.com\u002Fibizatomorrow\u002FDCST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fibizatomorrow\u002FDCST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fibizatomorrow\u002FDCST?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic | METR-LA \u003Cbr> PEMS-BAY | ST-nFBST | [Full Bayesian Significance Testing for Neural Networks in Traffic Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F245) | [Code](https:\u002F\u002Fgithub.com\u002Fliuzh-buaa\u002FST-nFBST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliuzh-buaa\u002FST-nFBST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliuzh-buaa\u002FST-nFBST?color=critical&style=social) | IJCAI\u003Cbr>2024\n| multi-source \u003Cbr> SSL | BikeIn \u003Cbr> BikeOut \u003Cbr> TaxiIn \u003Cbr> TaxiOut \u003Cbr> Air | MoSSL | [Multi-Modality Spatio-Temporal Forecasting via Self-Supervised Learning](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F223) | [Code](https:\u002F\u002Fgithub.com\u002Fbeginner-sketch\u002FMoSSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbeginner-sketch\u002FMoSSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbeginner-sketch\u002FMoSSL?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic \u003Cbr> CrossCity | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> DiDiCD \u003Cbr> DiDiSZ | pFedCTP | [Personalized Federated Learning for Cross-City Traffic Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F611) | [Code](https:\u002F\u002Fgithub.com\u002FZYuSdu\u002FpFedCTP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZYuSdu\u002FpFedCTP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZYuSdu\u002FpFedCTP?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SDformer | [SDformer: Transformer with Spectral Filter and Dynamic Attention for Multivariate Time Series Long-term Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F629) | [Code](https:\u002F\u002Fgithub.com\u002Fzhouziyu02\u002FSDformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhouziyu02\u002FSDformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhouziyu02\u002FSDformer?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SpecAR-Net | [SpecAR-Net: Spectrogram Analysis and Representation Network for Time Series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F433) | [Code](https:\u002F\u002Fgithub.com\u002FDongyi2go\u002FSpecAR_Net) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDongyi2go\u002FSpecAR_Net?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDongyi2go\u002FSpecAR_Net?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SCAT | [SCAT: A Time Series Forecasting with Spectral Central Alternating Transformers](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F622) | None | IJCAI\u003Cbr>2024\n| Traffic | Traffic \u003Cbr> ECG \u003Cbr> COVID-19 \u003Cbr> Wiki \u003Cbr> Solar | DIAN | [Decoupled Invariant Attention Network for Multivariate Time-series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F275) | [Code](https:\u002F\u002Fgithub.com\u002Fxhh39\u002FDIAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxhh39\u002FDIAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxhh39\u002FDIAN?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic | Wave \u003Cbr> Wind \u003Cbr> Air | EPL | [Self-adaptive Extreme Penalized Loss for Imbalanced Time Series Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F568) | [Code](https:\u002F\u002Fgithub.com\u002FLdiper\u002FEPL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLdiper\u002FEPL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLdiper\u002FEPL?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> Exchange | U-Mixer | [U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29337) | None | AAAI\u003Cbr>2024\n| Irregular |USHCN \u003Cbr> MIMIC-III \u003Cbr> MIMIC-IV \u003Cbr> Physionet-12 | GraFITi | [GraFITi: Graphs for Forecasting Irregularly Sampled Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29560) | [Code](https:\u002F\u002Fgithub.com\u002Fyalavarthivk\u002FGraFITi) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyalavarthivk\u002FGraFITi?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyalavarthivk\u002FGraFITi?color=critical&style=social) | AAAI\u003Cbr>2024\n| Traffic \u003Cbr> Flow | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | MultiSPANS | [MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635820) | [Code](https:\u002F\u002Fgithub.com\u002FSELGroup\u002FMultiSPANS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSELGroup\u002FMultiSPANS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSELGroup\u002FMultiSPANS?color=critical&style=social) | WSDM 2024\n| Multivariat | SIP \u003Cbr> NYC \u003Cbr> METR-LA | CreST | [CreST: A Credible Spatiotemporal Learning Framework for Uncertainty-aware Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635759) | None | WSDM 2024\n| Multivariat | Web Traffic \u003Cbr> Labour \u003Cbr> Traffic \u003Cbr> Tourism | HTS | [NeuralReconciler for Hierarchical Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635806) | None | WSDM 2024\n| Multivariat | NYC13 \u003Cbr> BikeNYC \u003Cbr> Chicago21 \u003Cbr> Chicago22 | CityCAN | [CityCAN: Causal Attention Network for Citywide Spatio-Temporal Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635764) | None | WSDM 2024\n| Multivariat | Solar \u003Cbr> Wiki \u003Cbr> Traffic \u003Cbr> ECG \u003Cbr> Electricity \u003Cbr> COVID-19 \u003Cbr> Weather \u003Cbr> ETT | FreTS | [Frequency-domain MLPs are More Effective Learners in Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Ff1d16af76939f476b5f040fd1398c0a3-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Faikunyi\u002FFreTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faikunyi\u002FFreTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faikunyi\u002FFreTS?color=critical&style=social) | NIPS\u003Cbr>2023\n| LLM4TS \u003Cbr> Zero Shot | Darts \u003Cbr> Monash \u003Cbr> Informer | - | [Large Language Models Are Zero-Shot Time Series Forecasters](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F3eb7ca52e8207697361b2c0fb3926511-Abstract-Conference.html) | [LLM](https:\u002F\u002Fgithub.com\u002Fngruver\u002Fllmtime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fngruver\u002Fllmtime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fngruver\u002Fllmtime?color=critical&style=social) | NIPS\u003Cbr>2023\n| Zero Shot | ECL \u003Cbr>ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Traffic \u003Cbr> Weather | ForecastPFN | [ForecastPFN: Synthetically-Trained Zero-Shot Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F0731f0e65559059eb9cd9d6f44ce2dd8-Abstract-Conference.html) | [TF](https:\u002F\u002Fgithub.com\u002Fabacusai\u002Fforecastpfn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fabacusai\u002Fforecastpfn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fabacusai\u002Fforecastpfn?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ECL \u003Cbr> Traffic \u003Cbr>ETT \u003Cbr> Weather | WITRAN | [WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F2938ad0434a6506b125d8adaff084a4a-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002FWater2sea\u002FWITRAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWater2sea\u002FWITRAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWater2sea\u002FWITRAN?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | Neural Lad | [Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling](https:\u002F\u002Fopenreview.net\u002Fforum?id=bISkJSa5Td) | None | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity | OneNet | [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fdd6a47bc0aad6f34aa5e77706d90cdc4-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fyfzhang114\u002FOneNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyfzhang114\u002FOneNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyfzhang114\u002FOneNet?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat \u003Cbr> Solar Irradiance| CAB \u003Cbr> TAM | CrossViVit | [Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context](https:\u002F\u002Fopenreview.net\u002Fforum?id=x5ZruOa4ax) | [Code](https:\u002F\u002Fgithub.com\u002Fgitbooo\u002FCrossViVit) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgitbooo\u002FCrossViVit?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgitbooo\u002FCrossViVit?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ECL \u003Cbr>ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Traffic \u003Cbr> Weather | Koopa | [Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fdd6a47bc0aad6f34aa5e77706d90cdc4-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FKoopa) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FKoopa?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FKoopa?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | GPVAR \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> CER-E\u003Cbr>AQI | TTS-IMP | [Taming Local Effects in Graph-based Spatiotemporal Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=x2PH6q32LR) | [Code](https:\u002F\u002Fgithub.com\u002FGraph-Machine-Learning-Group\u002Ftaming-local-effects-stgnns) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-Machine-Learning-Group\u002Ftaming-local-effects-stgnns?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-Machine-Learning-Group\u002Ftaming-local-effects-stgnns?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | PEMS08 \u003Cbr> AIR-BJ \u003Cbr> AIR-GZ | CaST | [Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment](https:\u002F\u002Fopenreview.net\u002Fforum?id=17Zkztjlgt) | [Code](https:\u002F\u002Fgithub.com\u002Fyutong-xia\u002FCaST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyutong-xia\u002FCaST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyutong-xia\u002FCaST?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | PEMS08 \u003Cbr> METR-LA \u003Cbr> NYC Taxi \u003Cbr> NYC Bike | GPT-ST | [GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=nMH5cUaSj8) | [Code](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FGPT-ST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHKUDS\u002FGPT-ST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHKUDS\u002FGPT-ST?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | Solar \u003Cbr> Wiki \u003Cbr> Traffic \u003Cbr> COVID-19 | FourierGNN | [FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fdc1e32dd3eb381dbc71482f6a96cbf86-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Faikunyi\u002FFourierGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faikunyi\u002FFourierGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faikunyi\u002FFourierGNN?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic | SimMTM | [SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F5f9bfdfe3685e4ccdbc0e7fb29cccf2a-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FSimMTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FSimMTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FSimMTM?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | BasisFormer | [BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fe150e6d0a1e5214740c39c6e4503ba7a-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fnzl5116190\u002FBasisformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnzl5116190\u002FBasisformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnzl5116190\u002FBasisformer?color=critical&style=social) | NIPS\u003Cbr>2023\n| Irregular | Neonate \u003Cbr> Traffic \u003Cbr> MIMIC \u003Cbr> StackOverflow \u003Cbr> BookOrder \u003Cbr> Exchange \u003Cbr> ETT \u003Cbr> ILI\u003Cbr> Weather| ContiFormer | [ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F9328208f88ec69420031647e6ff97727-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSeqML\u002Ftree\u002Fmain\u002FContiFormer) | NIPS\u003Cbr>2023\n| Multivariat | Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> ETT | SAN | [Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F2e19dab94882bc95ed094c4399cfda02-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Ficantnamemyself\u002FSAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ficantnamemyself\u002FSAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ficantnamemyself\u002FSAN?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | DeepTime | [ Learning Deep Time-index Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=pgcfCCNQXO) | [Code](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002FDeepTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsalesforce\u002FDeepTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsalesforce\u002FDeepTime?color=critical&style=social) | ICML\u003Cbr>2023\n| Multivariat | Crime \u003Cbr> CHI-Taxi \u003Cbr> NYC-Bike \u003Cbr> NYC-Taxi\u003Cbr> CHI-House\u003Cbr> NYC-House | GraphST | [Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation](https:\u002F\u002Fopenreview.net\u002Fforum?id=LVARH5wXM9) | [Code](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FGraphST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHKUDS\u002FGraphST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHKUDS\u002FGraphST?color=critical&style=social) | ICML\u003Cbr>2023\n| Multivariat | Synthetic \u003Cbr> Taxi \u003Cbr> Electricity \u003Cbr> Traffic | FeatureP | [Feature Programming for Multivariate Time Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=LVARH5wXM9) | [Code](https:\u002F\u002Fgithub.com\u002FSirAlex900\u002FFeatureProgramming) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSirAlex900\u002FFeatureProgramming?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSirAlex900\u002FFeatureProgramming?color=critical&style=social) | ICML\u003Cbr>2023\n| Multivariat | NorPool \u003Cbr> Caiso \u003Cbr> Weather \u003Cbr> ETT \u003Cbr> Wind \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Exchange | TimeDiff | [Non-autoregressive Conditional Diffusion Models for Time Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=wZsnZkviro) | None| ICML\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | MICN | [MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=zt53IDUR1U) | [Code](https:\u002F\u002Fgithub.com\u002Fwanghq21\u002FMICN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwanghq21\u002FMICN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwanghq21\u002FMICN?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> ILI \u003Cbr> Traffic | Crossformer | [Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vSVLM2j9eie) | [Code](https:\u002F\u002Fgithub.com\u002FThinklab-SJTU\u002FCrossformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FThinklab-SJTU\u002FCrossformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FThinklab-SJTU\u002FCrossformer?color=critical&style=social) | ICLR\u003Cbr>2023\n| Forecast \u003Cbr> Imputation \u003Cbr> Classifi \u003Cbr> AnomalyDet | ETT \u003Cbr> M4 \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr>SMD,MSL \u003Cbr> SMAP,SWaT \u003Cbr> PSM | TimesNet | [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https:\u002F\u002Fopenreview.net\u002Fforum?id=ju_Uqw384Oq) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FTime-Series-Library?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FTime-Series-Library?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | | Meta-SSM | [Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=7C9aRX2nBf2) | [Code](https:\u002F\u002Fgithub.com\u002Fjohn-x-jiang\u002Fmeta_ssm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjohn-x-jiang\u002Fmeta_ssm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjohn-x-jiang\u002Fmeta_ssm?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Weather | FSNet | [Learning Fast and Slow for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=q-PbpHD3EOk) | [Code](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Ffsnet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsalesforce\u002Ffsnet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsalesforce\u002Ffsnet?color=critical&style=social) | ICLR\u003Cbr>2023\n| Robust \u003Cbr> Multivariat | Traffic \u003Cbr> Taxi \u003Cbr> Wiki \u003Cbr> Electricity | | [Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms](https:\u002F\u002Fopenreview.net\u002Fforum?id=ctmLBs8lITa) | [Amazon](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluonts\u002Ftree\u002Fdev\u002Fsrc\u002Fgluonts\u002Fnursery) | ICLR\u003Cbr>2023\n| Multivariat | Electricity \u003Cbr> Crypto \u003Cbr> M4 \u003Cbr> Traffic \u003Cbr> Exchange | KNF | [Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts](https:\u002F\u002Fopenreview.net\u002Fforum?id=kUmdmHxK5N) | [Code](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002FKNF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002FKNF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002FKNF?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Exchange | SpaceTime | [Effectively Modeling Time Series with Simple Discrete State Spaces](https:\u002F\u002Fopenreview.net\u002Fforum?id=2EpjkjzdCAa) | [Code](https:\u002F\u002Fgithub.com\u002FHazyResearch\u002Fspacetime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHazyResearch\u002Fspacetime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHazyResearch\u002Fspacetime?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | Weather \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> ILI \u003Cbr> ETT | PatchTST | [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https:\u002F\u002Fopenreview.net\u002Fforum?id=Jbdc0vTOcol) | [Code](https:\u002F\u002Fgithub.com\u002Fyuqinie98\u002FPatchTST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuqinie98\u002FPatchTST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuqinie98\u002FPatchTST?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | Exchange \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> ILI | Scaleformer | [Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=sCrnllCtjoE) | [Code](https:\u002F\u002Fgithub.com\u002FBorealisAI\u002Fscaleformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBorealisAI\u002Fscaleformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBorealisAI\u002Fscaleformer?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat \u003Cbr> classification \u003Cbr> AnomalyDec | Electricity \u003Cbr> Weather \u003Cbr> ETTm1 \u003Cbr> MSL \u003Cbr> SMD \u003Cbr> SMAP | SBT | [Sparse Binary Transformers for Multivariate Time Series Modeling](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3580305.3599508) | [Code](https:\u002F\u002Fgithub.com\u002Fmattgorb\u002Fsparse-binary-transformers) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmattgorb\u002Fsparse-binary-transformers?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmattgorb\u002Fsparse-binary-transformers?color=critical&style=social) | KDD\u003Cbr>2023\n| Multivariat | SIP \u003Cbr> METR-LA \u003Cbr> KnowAir \u003Cbr> Electricity | CauSTG | [Maintaining the Status Quo: Capturing Invariant Relations for OOD Spatiotemporal Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | [Code](https:\u002F\u002Fgithub.com\u002Fzzyy0929\u002FKDD23-CauSTG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzzyy0929\u002FKDD23-CauSTG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzzyy0929\u002FKDD23-CauSTG?color=critical&style=social) | KDD\u003Cbr>2023\n| Robust \u003Cbr> Multivariat | PEMS-BAY \u003Cbr> PEMS04 | RDAT | [Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599492) | [Code](https:\u002F\u002Fgithub.com\u002Fusail-hkust\u002FRDAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fusail-hkust\u002FRDAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fusail-hkust\u002FRDAT?color=critical&style=social) | KDD\u003Cbr>2023\n| Multivariat | Beijing \u003Cbr> Chengdu \u003Cbr> Harbin | Frigate | [Frigate: Frugal Spatio-temporal Forecasting on Road Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599357) | [Code](https:\u002F\u002Fgithub.com\u002Fidea-iitd\u002Ffrigate) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fidea-iitd\u002Ffrigate?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fidea-iitd\u002Ffrigate?color=critical&style=social) | KDD\u003Cbr>2023\n|Multivariat | XC-Traffic \u003Cbr> NYC-Traffic | GCIM | [Generative Causal Interpretation Model for Spatio-Temporal Representation Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599363) | None | KDD\u003Cbr>2023\n| Multivariat | Tourism \u003Cbr> Labour \u003Cbr> Wiki \u003Cbr> Flu-Symptoms \u003Cbr> FB-Survey | PROFHiT | [When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FProfhit) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FProfhit?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FProfhit?color=critical&style=social) | KDD\u003Cbr>2023\n| Multivariat \u003Cbr> Under Miss | AQI-36 \u003Cbr> AQI \u003Cbr> PEMS-BAY \u003Cbr> CER-E \u003Cbr> Healthcare \u003Cbr> SMAP | MIDM | [An Observed Value Consistent Diffusion Model for Imputing Missing Values in Multivariate Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599257) | [Author](http:\u002F\u002Fhome.ustc.edu.cn\u002F~wx309\u002F) | KDD\u003Cbr>2023\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> etc.| Localised | [Localised Adaptive Spatial-Temporal Graph Neural Network](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599418) | None | KDD\u003Cbr>2023\n| Multivariat | PEMS3-Stream | PECPM | [Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599463) | None | KDD\u003Cbr>2023\n| Multivariat | Tourism \u003Cbr> Wiki \u003Cbr> Traffic | HPO | [Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | None | KDD\u003Cbr>2023 \n| Multivariat | Weather \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> ETT | TSMixer | [TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599533) | None| KDD\u003Cbr>2023\n| Transfer \u003Cbr> Traffic \u003Cbr> Forecasting | PEMSD7M \u003Cbr> PEMSD7M \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | TransGTR | [Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | [Author](https:\u002F\u002Fgithub.com\u002FKL4805) | KDD\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Weather \u003Cbr> ILI | DLinear | [Are Transformers Effective for Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26317) | [Code](https:\u002F\u002Fgithub.com\u002Fcure-lab\u002FLTSF-Linear) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcure-lab\u002FLTSF-Linear?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcure-lab\u002FLTSF-Linear?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> PEMSD7M | STC-Dropout | [Easy Begun Is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25590) | [Code](https:\u002F\u002Fgithub.com\u002FUrban-Computing\u002FSTC-Dropout) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUrban-Computing\u002FSTC-Dropout?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUrban-Computing\u002FSTC-Dropout?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | BJ-Bike \u003Cbr> NYC-Bike | STNSCM | [Spatio-Temporal Neural Structural Causal Models for Bike Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25542) | [Code](https:\u002F\u002Fgithub.com\u002FEternityZY\u002FSTNSCM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEternityZY\u002FSTNSCM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEternityZY\u002FSTNSCM?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | XC-Trans \u003Cbr> XC-Speed | CCHMM | [Causal Conditional Hidden Markov Model for Multimodal Traffic Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25619) | [Code](https:\u002F\u002Fgithub.com\u002FEternityZY\u002FCCHMM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEternityZY\u002FCCHMM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEternityZY\u002FCCHMM?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | NYCBike1 \u003Cbr> NYCBike2 \u003Cbr> NYCTaxi \u003Cbr> BJTaxi | ST-SSL | [Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25555) | [Code](https:\u002F\u002Fgithub.com\u002FEcho-Ji\u002FST-SSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEcho-Ji\u002FST-SSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEcho-Ji\u002FST-SSL?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | PV-US \u003Cbr> CER-En | SGP | [Scalable Spatiotemporal Graph Neural Networks](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25880) | [Code](https:\u002F\u002Fgithub.com\u002FGraph-Machine-Learning-Group\u002Fsgp) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-Machine-Learning-Group\u002Fsgp?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-Machine-Learning-Group\u002Fsgp?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | Electricity \u003Cbr> Solar \u003Cbr> PEMS-BAY \u003Cbr> METR-LA | SRD | [Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25915) | [Code](https:\u002F\u002Fgithub.com\u002FArthur-Null\u002FSRD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FArthur-Null\u002FSRD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FArthur-Null\u002FSRD?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity | InfoTS | [Time Series Contrastive Learning with Information-Aware Augmentations](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25575) | [Code](https:\u002F\u002Fgithub.com\u002Fchengw07\u002FInfoTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchengw07\u002FInfoTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchengw07\u002FInfoTS?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | PhysioNet \u003Cbr> MIMIC-III \u003Cbr> Activity \u003Cbr> Appliances Energy | PrimeNet | [PrimeNet: Pre-training for Irregular Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25876) | [Code](https:\u002F\u002Fgithub.com\u002Franakroychowdhury\u002FPrimeNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Franakroychowdhury\u002FPrimeNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Franakroychowdhury\u002FPrimeNet?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | Electricity \u003Cbr> ETT \u003Cbr> Weather | Dish-TS | [Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25914) | [Code](https:\u002F\u002Fgithub.com\u002Fweifantt\u002FDish-TS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fweifantt\u002FDish-TS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fweifantt\u002FDish-TS?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | NHITS | [NHITS: Neural Hierarchical Interpolation for Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25854) | [Code](https:\u002F\u002Fgithub.com\u002FNixtla\u002Fneuralforecast) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNixtla\u002Fneuralforecast?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNixtla\u002Fneuralforecast?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> ETT \u003Cbr> Weather | MegaCRN | [Spatio-Temporal Meta-Graph Learning for Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25976) | [Code](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FMegaCRN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa20\u002FMegaCRN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa20\u002FMegaCRN?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | Santa \u003Cbr> Traffic | NEC+ | [An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26276) | [Code](https:\u002F\u002Fgithub.com\u002Fdavidanastasiu\u002FNECPlus) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdavidanastasiu\u002FNECPlus?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdavidanastasiu\u002FNECPlus?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Extreme MTSF | Electricity \u003Cbr> Solar \u003Cbr> Weather \u003Cbr> Traffic | WaveForM | [WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26276) | [Code](https:\u002F\u002Fgithub.com\u002FalanyoungCN\u002FWaveForM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FalanyoungCN\u002FWaveForM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FalanyoungCN\u002FWaveForM?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> NYCTaxi \u003Cbr> CHBike \u003Cbr> TDrive | PDFormer | [PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25556) | [Code](https:\u002F\u002Fgithub.com\u002FBUAABIGSCity\u002FPDFormer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBUAABIGSCity\u002FPDFormer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBUAABIGSCity\u002FPDFormer?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | AmapBeijing \u003Cbr> AmapChengdu | STGNPP | [Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26669) | None | AAAI\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | InParformer | [InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25845) | None | AAAI\u003Cbr>2023\n| Multivariat | Tourism \u003Cbr> Labour \u003Cbr> M5 | SLOTH | [SLOTH: Structured Learning and Task-Based Optimization for Time Series Forecasting on Hierarchies](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26350) | None | AAAI\u003Cbr>2023 \n| Multivariat | Wind \u003Cbr> Solar | eForecaster | [eForecaster: Unifying Electricity Forecasting with Robust, Flexible, and Explainable Machine Learning Algorithms](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26853) | None | AAAI\u003Cbr>2023 \n| Multivariat | NYCTaxi \u003Cbr> PEMS04 | AutoSTL | [AutoSTL: Automated Spatio-Temporal Multi-Task Learning](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25616) | None | AAAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> PEMS-BAY | Trafformer | [Trafformer: Unify Time and Space in Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1609\u002Faaai.v37i7.25980) | None| AAAI\u003Cbr>2023\n| Multivariat | Electricity \u003Cbr> PM2.5 \u003Cbr> Exchange | DeLELSTM | [DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F478) | [Code](https:\u002F\u002Fgithub.com\u002Fwangcq01\u002FDeLELSTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwangcq01\u002FDeLELSTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwangcq01\u002FDeLELSTM?color=critical&style=social) | IJCAI\u003Cbr>2023 \n| Multivariat | NYC-Bike \u003Cbr> PEMS-BAY \u003Cbr> PEMS08 | ReMo | [Not Only Pairwise Relationships: Fine-Grained Relational Modeling for Multivariate Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F491) | [Code](https:\u002F\u002Fgithub.com\u002Fbeginner-sketch\u002Fgmrl) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbeginner-sketch\u002Fgmrl?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbeginner-sketch\u002Fgmrl?color=critical&style=social) | IJCAI\u003Cbr>2023 \n| Multivariat | NASA | MetePFL | [Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F393) | [Code](https:\u002F\u002Fgithub.com\u002Fshengchaochen82\u002FMetePFL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshengchaochen82\u002FMetePFL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshengchaochen82\u002FMetePFL?color=critical&style=social) | IJCAI\u003Cbr>2023 \n| Multivariat | Hurricane \u003Cbr> Climate | Self-Recover | [Self-Recover: Forecasting Block Maxima in Time Series from Predictors with Disparate Temporal Coverage Using Self-Supervised Learning](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F4141) | None | IJCAI\u003Cbr>2023 \n| Multivariat | Weather \u003Cbr> Traffc \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> ILI | SMARTformer | [SMARTformer: Semi-Autoregressive Transformer with Efficient Integrated Window Attention for Long Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F241) | None| IJCAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> Beijing \u003Cbr> Xiamen | INCREASE | [INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3543507.3583525) | [TF](https:\u002F\u002Fgithub.com\u002Fzhengchuanpan\u002FINCREASE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhengchuanpan\u002FINCREASE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhengchuanpan\u002FINCREASE?color=critical&style=social) | WWW 2023\n| Multivariat | MQPS \u003Cbr> ETT \u003Cbr> Electricity | KAE-Informer | [KAE-Informer: A Knowledge Auto-Embedding Informer for Forecasting Long-Term Workloads of Microservices](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3543507.3583288) | [Code](https:\u002F\u002Fgithub.com\u002Fcitsjtu2020\u002FKAE-Informer-MQPS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) | WWW 2023\n| Multivariat | Typhoon-JP \u003Cbr> COVID-JP \u003Cbr> Hurricane-US | MemeSTN | [Learning Social Meta-knowledge for Nowcasting Human Mobility in Disaster](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3543507.3583991) | [Code](https:\u002F\u002Fgithub.com\u002Fcitsjtu2020\u002FKAE-Informer-MQPS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) | WWW 2023\n| Multivariat | NYC \u003Cbr> Chicago | EALGAP | [Extreme-Aware Local-Global Attention for Spatio-Temporal Urban Mobility Learning](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184645) | [Keras](https:\u002F\u002Fgithub.com\u002FHuiqunHuang\u002FEALGAP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHuiqunHuang\u002FEALGAP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHuiqunHuang\u002FEALGAP?color=critical&style=social) | ICDE 2023 \n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DyHSL | [Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184800) | [Code](https:\u002F\u002Fgithub.com\u002FYushengZhao\u002FDyHSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYushengZhao\u002FDyHSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYushengZhao\u002FDyHSL?color=critical&style=social) | ICDE 2023 \n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STWave | [When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184591) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FSTWave) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FSTWave?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FSTWave?color=critical&style=social) | ICDE 2023 \n| Multivariat | Seattle \u003Cbr> PEMS04 \u003Cbr> PEMS08 | SSTBAN | [Self-Supervised Spatial-Temporal Bottleneck Attentive Network for Efficient Long-term Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184658) | [Code](https:\u002F\u002Fgithub.com\u002FguoshnBJTU\u002FSSTBAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FguoshnBJTU\u002FSSTBAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FguoshnBJTU\u002FSSTBAN?color=critical&style=social) | ICDE 2023 \n| Multivariat | PEMSD4 \u003Cbr> PEMSD8 \u003Cbr> AirBJ \u003Cbr> TrafficSIP | MGTF | [A Multi-graph Fusion Based Spatiotemporal Dynamic Learning Framework](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3539597.3570396) | [Author](http:\u002F\u002Fhome.ustc.edu.cn\u002F~wx309\u002F) | WSDM 2023\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08| STAEformer | [Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615136) | [Code](https:\u002F\u002Fgithub.com\u002FXDZhelheim\u002FSTAEformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FXDZhelheim\u002FSTAEformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FXDZhelheim\u002FSTAEformer?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | TrendGCN | [Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614868) | [Code](https:\u002F\u002Fgithub.com\u002Fjuyongjiang\u002FTrendGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjuyongjiang\u002FTrendGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjuyongjiang\u002FTrendGCN?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Exchange | GCformer | [GCformer: An Efficient Solution for Accurate and Scalable Long-Term Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614868) | [Code](https:\u002F\u002Fgithub.com\u002FYanjun-Zhao\u002FGCformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYanjun-Zhao\u002FGCformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYanjun-Zhao\u002FGCformer?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic | Seq2Peak | [Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615159) | [Code](https:\u002F\u002Fgithub.com\u002Fzhangzw16\u002FSeq2Peak) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhangzw16\u002FSeq2Peak?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhangzw16\u002FSeq2Peak?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> NYC Crime \u003Cbr> CHI Crime | CL4ST | [Spatio-Temporal Meta Contrastive Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615065) | [Code](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FCL4ST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHKUDS\u002FCL4ST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHKUDS\u002FCL4ST?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | NYC Bike \u003Cbr> NYC Taxi | MLPST | [MLPST: MLP is All You Need for Spatio-Temporal Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614969) | [Author](https:\u002F\u002Fgithub.com\u002FZhang-Zijian) | CIKM\u003Cbr>2023 \n| Multivariat | TaxiBJ \u003Cbr> BikeNYC | MC-STL | [Mask- and Contrast-Enhanced Spatio-Temporal Learning for Urban Flow Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614958) | [Code](https:\u002F\u002Fgithub.com\u002FCodeZx6\u002FMCSTL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCodeZx6\u002FMCSTL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCodeZx6\u002FMCSTL?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | PeMS \u003Cbr> Beijing \u003Cbr> Electricity \u003Cbr> COVID-CHI | MemDA | [MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615136) | [Code](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FUrban_Concept_Drift) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa20\u002FUrban_Concept_Drift?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa20\u002FUrban_Concept_Drift?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Cross City \u003Cbr> Traffic | PEMS-BAY \u003Cbr> METR-LA \u003Cbr> Chengdu \u003Cbr> Shenzhen| TPB | [Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614829) | [Code](https:\u002F\u002Fgithub.com\u002Fzhyliu00\u002FTPB) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhyliu00\u002FTPB?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhyliu00\u002FTPB?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMSD7M | UAGCRN | [Enhancing Spatio-temporal Traffic Prediction through Urban Human Activity Analysis](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614867) | [TF](https:\u002F\u002Fgithub.com\u002FSuminHan\u002FTraffic-UAGCRNTF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSuminHan\u002FTraffic-UAGCRNTF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSuminHan\u002FTraffic-UAGCRNTF?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | Complaint \u003Cbr> NYC Taxi | PromptST | [PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615159) | [Code](https:\u002F\u002Fgithub.com\u002FZhang-Zijian\u002FPromptST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhang-Zijian\u002FPromptST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZhang-Zijian\u002FPromptST?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS08 | HIEST | [Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614910) | [Code](https:\u002F\u002Fgithub.com\u002FVAN-QIAN\u002FCIKM23-HIEST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVAN-QIAN\u002FCIKM23-HIEST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVAN-QIAN\u002FCIKM23-HIEST?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Traffic | TemDep | [TemDep: Temporal Dependency Priority for Multivariate Time Series Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615164) | [Code](https:\u002F\u002Fgithub.com\u002Fzivgogogo\u002FTemDep) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzivgogogo\u002FTemDep?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzivgogogo\u002FTemDep?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Traffic | BJ-Center \u003Cbr> METR-LA | ST-MoE | [ST-MoE: Spatio-Temporal Mixture-of-Experts for Debiasing in Traffic Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615068) | None | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Traffic \u003Cbr> Exchange | AVGNets | [Learning Visibility Attention Graph Representation for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615289) | None | CIKM\u003Cbr>2023 \n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STGBN | [Spatial-Temporal Graph Boosting Networks: Enhancing Spatial-Temporal Graph Neural Networks via Gradient Boosting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615066) | None | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> ILI \u003Cbr> Exchange | FAMC-Net | [FAMC-Net: Frequency Domain Parity Correction Attention and Multi-Scale Dilated Convolution for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614876) | None| CIKM\u003Cbr>2023 \n| Cross City \u003Cbr> Traffic | NYC \u003Cbr> Chicago \u003Cbr> Nashville | CARPG | [CARPG: Cross-City Knowledge Transfer for Traffic Accident Prediction via Attentive Region-Level Parameter Generation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3614802) | None| CIKM\u003Cbr>2023 \n| Traffic | SPEED \u003Cbr> FLOW | CANet | [Clustering-property Matters: A Cluster-aware Network for Large Scale Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615253) | None | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic | DSformer | [DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3614851) | None | CIKM\u003Cbr>2023 \n| Multivariat | Wufu | MODE | [Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615487) | None | CIKM\u003Cbr>2023 \n| Multivariat | NYC | MetaRSTP | [Region Profile Enhanced Urban Spatio-Temporal Prediction via Adaptive Meta-Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615027) | None | CIKM\u003Cbr>2023 \n| Multivariat | SIP \u003Cbr> NYC \u003Cbr> METR-LA | G2S | [Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch22) | None | SDM 2023\n| Multivariat | Solar \u003Cbr> PEMS-BAY \u003Cbr> Electricity | ERL | [Time-delayed Multivariate Time Series Predictions](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch37) | None | SDM 2023\n| Multivariat | Weather2K | Weather2K | [Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations](https:\u002F\u002Fproceedings.mlr.press\u002Fv206\u002Fzhu23a.html) | [Weather2K](https:\u002F\u002Fgithub.com\u002Fbycnfz\u002Fweather2k\u002F) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbycnfz\u002Fweather2k?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbycnfz\u002Fweather2k?color=critical&style=social) | AISTATS 2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | FiLM | [FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=zTQdHSQUQWc) | [Code](https:\u002F\u002Fgithub.com\u002Ftianzhou2011\u002FFiLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftianzhou2011\u002FFiLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftianzhou2011\u002FFiLM?color=critical&style=social) | NeurIPS 2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Weather | LaST | [Learning Latent Seasonal-Trend Representations for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=C9yUwd72yy) | [Code](https:\u002F\u002Fgithub.com\u002Fzhycs\u002FLaST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhycs\u002FLaST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhycs\u002FLaST?color=critical&style=social) | NeurIPS 2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | WaveBound | [WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vsNQkquutZk) | [Code](https:\u002F\u002Fgithub.com\u002Fchoyi0521\u002FWaveBound) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchoyi0521\u002FWaveBound?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchoyi0521\u002FWaveBound?color=critical&style=social) | NeurIPS 2022\n| Multivariat | COVID-19 \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> Temperature \u003Cbr> Bytom \u003Cbr> Wind | ZFC-SHCN | [Time-Conditioned Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=2Ln-TWxVtf) | [Future](https:\u002F\u002Fgithub.com\u002Fzfcshcn\u002FZFC-SHCN) | NeurIPS 2022\n| Multivariat | ETT \u003Cbr> Traffic \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | SCINet | [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https:\u002F\u002Fopenreview.net\u002Fforum?id=AyajSjTAzmg) | [Code](https:\u002F\u002Fgithub.com\u002Fcure-lab\u002FSCINet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcure-lab\u002FSCINet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcure-lab\u002FSCINet?color=critical&style=social) | NeurIPS 2022\n| Multivariat | Electricity \u003Cbr> ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Traffic \u003Cbr> Weather | NonstaTransf | [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=ucNDIDRNjjv) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FNonstationary_Transformers) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FNonstationary_Transformers?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FNonstationary_Transformers?color=critical&style=social) | NeurIPS 2022\n| Multivariat | Traffic \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> PEMS07(M) \u003Cbr> PEMS-BAY | TPGNN | [Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=pMumil2EJh) | [Future](https:\u002F\u002Fgithub.com\u002Fzyplanet\u002FTPGNN) | NeurIPS 2022\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DSTAGNN | [DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Flan22a.html) | [Code](https:\u002F\u002Fgithub.com\u002FSYLan2019\u002FDSTAGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSYLan2019\u002FDSTAGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSYLan2019\u002FDSTAGNN?color=critical&style=social) | ICML\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | FEDformer | [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fzhou22g.html) | [Code](https:\u002F\u002Fgithub.com\u002FMAZiqing\u002FFEDformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMAZiqing\u002FFEDformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMAZiqing\u002FFEDformer?color=critical&style=social) | ICML\u003Cbr>2022\n| Multivariat | Traffic \u003Cbr> Electricity \u003Cbr> Wiki \u003Cbr> Sales | DAF | [DAF-Domain Adaptation for Time Series Forecasting via Attention Sharing](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fjin22d.html) | None| ICML\u003Cbr>2022\n| Multivariat | Electricity \u003Cbr> Solar \u003Cbr> Fred MD \u003Cbr> KDD Cup | TACTiS \u003Cbr> (Copulas,\u003Cbr> Trans) | [TACTiS: Transformer-Attentional Copulas for Time Series](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fdrouin22a.html) | [Code](https:\u002F\u002Fgithub.com\u002Fservicenow\u002Ftactis) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fservicenow\u002Ftactis?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fservicenow\u002Ftactis?color=critical&style=social) | ICML\u003Cbr>2022\n| Multivariat | French \u003Cbr> Electricity | AgACI | [Adaptive Conformal Predictions for Time Series](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07282) | [Python,R](https:\u002F\u002Fgithub.com\u002Fmzaffran\u002FAdaptiveConformalPredictionsTimeSeries) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmzaffran\u002FAdaptiveConformalPredictionsTimeSeries?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmzaffran\u002FAdaptiveConformalPredictionsTimeSeries?color=critical&style=social) | ICML\u003Cbr>2022\n| Traffic Speed | NAVER-Seoul \u003Cbr> METR-LA | PM-MemNet \u003Cbr> (Mem,KNN) | [Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=wwDg3bbYBIq) | [Code](https:\u002F\u002Fgithub.com\u002FHyunWookL\u002FPM-MemNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHyunWookL\u002FPM-MemNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHyunWookL\u002FPM-MemNet?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> COVID-19,etc | TAMP-S2GCNets \u003Cbr> (GCN,AR, \u003Cbr> Topological Features) | [TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=wv6g8fWLX2q) | [Code](https:\u002F\u002Fwww.dropbox.com\u002Fsh\u002Fn0ajd5l0tdeyb80\u002FAABGn-ejfV1YtRwjf_L0AOsNa?dl=0) | ICLR\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather | CoST | [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=PilZY3omXV2) | [Code](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002FCoST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsalesforce\u002FCoST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsalesforce\u002FCoST?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> M4 \u003Cbr> CASIO \u003Cbr> NP | DEPTS | [DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=AJAR-JgNw__) | [Code](https:\u002F\u002Fgithub.com\u002Fweifantt\u002FDEPTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fweifantt\u002FDEPTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fweifantt\u002FDEPTS?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Wind \u003Cbr> App Flow | Pyraformer | [Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=0EXmFzUn5I) | [Code](https:\u002F\u002Fgithub.com\u002Falipay\u002FPyraformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falipay\u002FPyraformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falipay\u002FPyraformer?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> M4 \u003Cbr> Air Quality \u003Cbr> Nasdaq | RevIN | [Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift](https:\u002F\u002Fopenreview.net\u002Fforum?id=cGDAkQo1C0p) | [Code](https:\u002F\u002Fgithub.com\u002Fts-kim\u002FRevIN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fts-kim\u002FRevIN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fts-kim\u002FRevIN?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS08 | D2STGNN | [Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting](https:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol15\u002Fp2733-shao.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Fzezhishao\u002FD2STGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzezhishao\u002FD2STGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzezhishao\u002FD2STGNN?color=critical&style=social) | VLDB 2022\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 | STEP | [Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539396) | [Code](https:\u002F\u002Fgithub.com\u002Fzezhishao\u002FSTEP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzezhishao\u002FSTEP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzezhishao\u002FSTEP?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | Solar \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Wind \u003Cbr> NYCBike \u003Cbr> NYCTaxi | ESG | [Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539274) | [Code](https:\u002F\u002Fgithub.com\u002FLiuZH-19\u002FESG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiuZH-19\u002FESG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiuZH-19\u002FESG?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | METR-LA \u003Cbr> Solar \u003Cbr> Traffic \u003Cbr> ECG5000 | VSF | [Multi-Variate Time Series Forecasting on Variable Subsets](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539394) | [Code,dgl](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fvsf-time-series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgoogle\u002Fvsf-time-series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgoogle\u002Fvsf-time-series?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | DC Bike \u003Cbr> DC Taxi | CrossTReS | [Selective Cross-City Transfer Learning for Traffic Prediction via Source City Region Re-Weighting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539250) | [Code,dgl](https:\u002F\u002Fgithub.com\u002FKL4805\u002FCrossTReS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKL4805\u002FCrossTReS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKL4805\u002FCrossTReS?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Electricity | Quatformer | [Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539234) | [MRA-BGCN Author](https:\u002F\u002Fscholar.google.com\u002Fcitations?hl=zh-CN&user=dMg_soMAAAAJ&view_op=list_works&sortby=pubdate) \u003Cbr> None Code | KDD\u003Cbr>2022\n| Multivariat | NYCBike \u003Cbr> NYCTaxi \u003Cbr> PEMS03 \u003Cbr> PEMS08 | GMSDR | [MSDR: Multi-Step Dependency Relation Networks for Spatial Temporal Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539397) | [Code](https:\u002F\u002Fgithub.com\u002Fdcliu99\u002FMSDR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdcliu99\u002FMSDR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdcliu99\u002FMSDR?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | Hangzhou \u003Cbr> NYC | DTIGNN | [Modeling Network-level Traffic Flow Transitions on Sparse Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539236) | [Code](https:\u002F\u002Fgithub.com\u002Fshawlen\u002Fdtignn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshawlen\u002Fdtignn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshawlen\u002Fdtignn?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | Temperature \u003Cbr> Cloud cover \u003Cbr> Humidity \u003Cbr> Wind | CLCRN | [Conditional Local Convolution for Spatio-temporal Meteorological Forecasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai1716) | [Code](https:\u002F\u002Fgithub.com\u002FBIRD-TAO\u002FCLCRN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBIRD-TAO\u002FCLCRN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBIRD-TAO\u002FCLCRN?color=critical&style=social) | AAAI\u003Cbr>2022\n| Traffic Flow | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> PEMS07(M) \u003Cbr> PEMS07(L) | STG-NCDE | [Graph Neural Controlled Differential Equations for Traffic Forecasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai6502) | [Code](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FSTG-NCDE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjeongwhanchoi\u002FSTG-NCDE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjeongwhanchoi\u002FSTG-NCDE?color=critical&style=social) | AAAI\u003Cbr>2022\n| Traffic Flow | GT-221 \u003Cbr> WRS-393 \u003Cbr> ZGC-564 | STDEN | [STDEN: Towards Physics-guided Neural Networks for Traffic Flow Prediction](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai211) | [Code](https:\u002F\u002Fgithub.com\u002FEcho-Ji\u002FSTDEN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEcho-Ji\u002FSTDEN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEcho-Ji\u002FSTDEN?color=critical&style=social) | AAAI\u003Cbr>2022\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> PEMS07(M) \u003Cbr> METR-LA | CATN | [CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai7403) | None | AAAI\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity | TS2Vec | [TS2Vec: Towards Universal Representation of Time Series](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai8809) | [Code](https:\u002F\u002Fgithub.com\u002Fyuezhihan\u002Fts2vec) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuezhihan\u002Fts2vec?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuezhihan\u002Fts2vec?color=critical&style=social) | AAAI\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather | Triformer | [Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F277) | [Code](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002Ftriformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frazvanc92\u002Ftriformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frazvanc92\u002Ftriformer?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | FOGS | [FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F545) | [Code](https:\u002F\u002Fgithub.com\u002Fkevin-xuan\u002FFOGS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkevin-xuan\u002FFOGS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkevin-xuan\u002FFOGS?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | PEMS04 \u003Cbr> PEMS08 \u003Cbr> RPCM | RGSL | [Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F328) | [Code](https:\u002F\u002Fgithub.com\u002Falipay\u002FRGSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falipay\u002FRGSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falipay\u002FRGSL?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | Air Quality \u003Cbr> Parking | DMGA | [Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F309) | None | IJCAI\u003Cbr>2022\n| Multivariat | YellowCab \u003Cbr> GreenCab \u003Cbr> Solar | ST-KMRN | [Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F304) | [Author](https:\u002F\u002Fgithub.com\u002Fmengcz13) | IJCAI\u003Cbr>2022\n| Multivariat | NYCTaxi \u003Cbr> NYCBike \u003Cbr> CHIBike \u003Cbr> BJTaxi \u003Cbr> Chengdu| STAN | [When Transfer Learning Meets Cross-City Urban Flow Prediction: Spatio-Temporal Adaptation Matters](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F282) | None | IJCAI\u003Cbr>2022\n| Multivariat | Hurricanes \u003Cbr> Ausgrid \u003Cbr> Weather | DeepExtrema | [DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F413) | [Code](https:\u002F\u002Fgithub.com\u002Fgalib19\u002FDeepExtrema-IJCAI22-) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgalib19\u002FDeepExtrema-IJCAI22-?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgalib19\u002FDeepExtrema-IJCAI22-?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | GoogleSymp \u003Cbr> Covid19 \u003Cbr> Power \u003Cbr> Tweet | CAMul | [CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512037) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FCAMul) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FCAMul?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FCAMul?color=critical&style=social) | WWW 2022\n| Multivariat | Electricity \u003Cbr> Stock | MRLF | [Multi-Granularity Residual Learning with Confidence Estimation for Time Series Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512056) | [Code](https:\u002F\u002Fgithub.com\u002FCMLF-git-dev\u002FMRLF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCMLF-git-dev\u002FMRLF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCMLF-git-dev\u002FMRLF?color=critical&style=social) | WWW 2022\n| Multivariat \u003Cbr> Classification \u003Cbr> Forecasting | MuJoCo \u003Cbr> Google Stock | EXIT | [EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512030) | [Code](https:\u002F\u002Fgithub.com\u002Fsheoyon-jhin\u002FEXIT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsheoyon-jhin\u002FEXIT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsheoyon-jhin\u002FEXIT?color=critical&style=social) | WWW 2022\n| Traffic Flow | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | ST-WA | [Towards Spatio- Temporal Aware Traffic Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835586) | [Code](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002FST-WA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frazvanc92\u002FST-WA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frazvanc92\u002FST-WA?color=critical&style=social) | ICDE 2022\n| Mobility \u003Cbr> Prediction | NYC \u003Cbr> Dallas \u003Cbr> Miami | SHIFT | [Translating Human Mobility Forecasting through Natural Language Generation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3488560.3498387) | [Hao Xue](https:\u002F\u002Fgithub.com\u002Fxuehaouwa) | WSDM 2022\n| Traffic Flow | TaxiBJ \u003Cbr> BikeNYC | ST-GSP | [ST-GSP: Spatial-Temporal Global Semantic Representation Learning for Urban Flow Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498444) | [Code](https:\u002F\u002Fgithub.com\u002Fk51\u002FSTGSP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fk51\u002FSTGSP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fk51\u002FSTGSP?color=critical&style=social) | WSDM 2022\n| Multivariat | Traffic \u003Cbr> Temperature | ReTime | [Retrieval Based Time Series Forecasting](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.13525#) | None| CIKM\u003Cbr>2022\n| Multivariat | Rainfall \u003Cbr> Traffic \u003Cbr> ETT \u003Cbr> Stock \u003Cbr> Climate | DXtreMM | [Deep Extreme Mixture Model for Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557282) | [Code](https:\u002F\u002Fgithub.com\u002FDXtreMM\u002FDXtreMM_TSF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDXtreMM\u002FDXtreMM_TSF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDXtreMM\u002FDXtreMM_TSF?color=critical&style=social) | CIKM\u003Cbr>2022\n| MTS Analysis \u003Cbr> MTS Forecasting \u003Cbr> Anormaly Detection | ETT \u003Cbr> Electricity \u003Cbr> SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT | MARINA | [MARINA: An MLP-Attention Model for Multivariate Time-Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557386) | None| CIKM\u003Cbr>2022\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | ResCAL | [Residual Correction in Real-Time Traffic Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557432) | None | CIKM\u003Cbr>2022\n| Model Selection | | AutoForecast | [AutoForecast: Automatic Time-Series Forecasting Model Selection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557241) | None | CIKM\u003Cbr>2022\n| Traffic Flow | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DastNet | [Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557294) | [Code](https:\u002F\u002Fgithub.com\u002FYihongT\u002FDASTNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYihongT\u002FDASTNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYihongT\u002FDASTNet?color=critical&style=social) | CIKM\u003Cbr>2022\n| Traffic Flow & Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | AutoSTS | [Automated Spatio-Temporal Synchronous Modeling with Multiple Graphs for Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557243) | YongLi THU | CIKM\u003Cbr>2022\n| Traffic Condition | TRCV-BJ \u003Cbr> TRCV-SH \u003Cbr> TRCV-ZZ | DuTraffic | [DuTraffic: Live Traffic Condition Prediction with Trajectory Data and Street Views at Baidu Maps](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557151) | None | CIKM\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> WTH \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Exchange | Linear | [Do Simpler Statistical Methods Perform Better in Multivariate Long Sequence Time-Series Forecasting?](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557585) | None | CIKM\u003Cbr>2022\n| Multivariat | Solar \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Exchange | MAGL | [Memory Augmented Graph Learning Networks for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557638) | None | CIKM\u003Cbr>2022\n| Multivariat | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> PEMS-BAY \u003Cbr> Electricity | STID | [Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557702) | [Code](https:\u002F\u002Fgithub.com\u002Fzezhishao\u002FSTID) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzezhishao\u002FSTID?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzezhishao\u002FSTID?color=critical&style=social) | CIKM\u003Cbr>2022\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS07 | ASTTN | [Adaptive Graph Spatial-Temporal Transformer Network for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3511808.3557540) | None | CIKM\u003Cbr>2022\n| Multivariat | Seoul | CGAN | [Context-aware Traffic Flow Forecasting in New Roads](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557566) | None | CIKM\u003Cbr>2022\n| Traffic Flow & Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS-M \u003Cbr> PEMS04 \u003Cbr> PEMS08 | ST-GAT | [ST-GAT: A Spatio-Temporal Graph Attention Network for Accurate Traffic Speed Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557705) | [Author](https:\u002F\u002Fgithub.com\u002FHanyang-HCC-Lab) | CIKM\u003Cbr>2022\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | HOMGNNs | [Higher-Order Masked Graph Neural Networks for Traffic Flow Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027720) | [Code](https:\u002F\u002Fgithub.com\u002Fmaisuiqianxun\u002FHOMGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmaisuiqianxun\u002FHOMGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmaisuiqianxun\u002FHOMGNN?color=critical&style=social) | ICDM 2022\n| Multivariat | M4 \u003Cbr> Electricity \u003Cbr> car-parts | TopAttn | [Topological Attention for Time Series Forecasting](https:\u002F\u002FNeurIPS.cc\u002FConferences\u002F2021\u002FScheduleMultitrack?event=26763) | [Code](https:\u002F\u002Fgithub.com\u002Fplus-rkwitt\u002FTAN)\u003Cbr> \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fplus-rkwitt\u002FTAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fplus-rkwitt\u002FTAN?color=critical&style=social) Future | NeurIPS 2021\n| Multivariat | Rossmann \u003Cbr> M5 \u003Cbr> Wiki | MisSeq | [MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F6b5754d737784b51ec5075c0dc437bf0-Abstract.html) | None | NeurIPS 2021\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | Autoformer | [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=J4gRj6d5Qm) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FAutoformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FAutoformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FAutoformer?color=critical&style=social) | NeurIPS 2021\n| Multivariat | PEMS04 \u003Cbr> PEMS08 \u003Cbr> Traffic \u003Cbr> ADI \u003Cbr> M4 ,etc | Error | [Adjusting for Autocorrelated Errors in Neural Networks for Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=tJ_CO8orSI) | [Code](https:\u002F\u002Fgithub.com\u002FDaikon-Sun\u002FAdjustAutocorrelation) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDaikon-Sun\u002FAdjustAutocorrelation?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDaikon-Sun\u002FAdjustAutocorrelation?color=critical&style=social) | NeurIPS 2021\n| Multivariat | Bytom \u003Cbr> Decentraland \u003Cbr> PEMS04 \u003Cbr> PEMS08| Z-GCNETs | [Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fchen21o.html) | [Code](https:\u002F\u002Fgithub.com\u002FZ-GCNETs\u002FZ-GCNETs) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-GCNETs\u002FZ-GCNETs?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZ-GCNETs\u002FZ-GCNETs?color=critical&style=social) | ICML\u003Cbr>2021\n| Multivariat | PEMS07(M) \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | Cov | [Conditional Temporal Neural Processes with Covariance Loss](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fyoo21b.html) | None | ICML\u003Cbr>2021\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PMU | GTS | [Discrete Graph Structure Learning for Forecasting Multiple Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=WEHSlH5mOk) | [Code](https:\u002F\u002Fgithub.com\u002Fchaoshangcs\u002FGTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchaoshangcs\u002FGTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchaoshangcs\u002FGTS?color=critical&style=social) | ICLR\u003Cbr>2021\n| Multivariat | Benz \u003Cbr> Air Quality \u003Cbr> FuelMoisture | framework | [A Transformer-based Framework for Multivariate Time Series Representation Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467401) | [Code](https:\u002F\u002Fgithub.com\u002Fgzerveas\u002Fmvts_transformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgzerveas\u002Fmvts_transformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgzerveas\u002Fmvts_transformer?color=critical&style=social) | KDD\u003Cbr>2021\n| Federated Multivariat | PEMS-BAY \u003Cbr> METR-LA | CNFGNN | [Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467371) | [Code](https:\u002F\u002Fgithub.com\u002Fmengcz13\u002FKDD2021_CNFGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmengcz13\u002FKDD2021_CNFGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmengcz13\u002FKDD2021_CNFGNN?color=critical&style=social) | KDD\u003Cbr>2021\n| Traffic Speed | PEMS04 \u003Cbr> PEMS08 \u003Cbr> England | DMSTGCN | [Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467275) | [Code](https:\u002F\u002Fgithub.com\u002Fliangzhehan\u002FDMSTGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliangzhehan\u002FDMSTGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliangzhehan\u002FDMSTGCN?color=critical&style=social) | KDD\u003Cbr>2021\n| Traffic Flow | PEMS07(M) \u003Cbr> PEMS07(L) \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STGODE | [Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467430) | [Code](https:\u002F\u002Fgithub.com\u002Fsquare-coder\u002FSTGODE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsquare-coder\u002FSTGODE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsquare-coder\u002FSTGODE?color=critical&style=social) | KDD\u003Cbr>2021\n| Multivariat | BikeNYC \u003Cbr> PEMS07(M) \u003Cbr> Electricity | ST-Norm | [ST-Norm: Spatial and Temporal Normalization for Multi-variate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467330) | [Code](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FST-Norm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJLDeng\u002FST-Norm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJLDeng\u002FST-Norm?color=critical&style=social) | KDD\u003Cbr>2021\n| Multivariat | DiDiXM \u003Cbr> DiDiCD | TrajNet | [TrajNet: A Trajectory-Based Deep Learning Model for Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467236) | None | KDD\u003Cbr>2021\n| Robust Forecasting | MIMIC-III \u003Cbr> USHCN \u003Cbr> KDD-CUP | DGM | [Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16145) | [Code](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | Guangzhou \u003Cbr> Seattle \u003Cbr> HZMetro , etc. | DSARF | [Deep Switching Auto-Regressive Factorization: Application to Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16907) | [Code](https:\u002F\u002Fgithub.com\u002Fostadabbas\u002FDSARF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fostadabbas\u002FDSARF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fostadabbas\u002FDSARF?color=critical&style=social) | AAAI\u003Cbr>2021\n|Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | FC-GAGA | [FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17114) | [TF](https:\u002F\u002Fgithub.com\u002Fboreshkinai\u002Ffc-gaga) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fboreshkinai\u002Ffc-gaga?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fboreshkinai\u002Ffc-gaga?color=critical&style=social) | AAAI\u003Cbr>2021\n|Traffic Speed | DiDiJiNan \u003Cbr> DiDiXiAn | HGCN | [Hierarchical Graph Convolution Network for Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16088) | [Code](https:\u002F\u002Fgithub.com\u002Fguokan987\u002FHGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fguokan987\u002FHGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fguokan987\u002FHGCN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity | Informer | [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17325) | [Code](https:\u002F\u002Fgithub.com\u002Fzhouhaoyi\u002FInformer2020) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhouhaoyi\u002FInformer2020?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhouhaoyi\u002FInformer2020?color=critical&style=social) | AAAI\u003Cbr>2021\n| Traffic Flow | NYCMetro \u003Cbr> NYC Bike \u003Cbr> NYC Taxi | MOTHER | [Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16603) | None | AAAI\u003Cbr>2021\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07(M) \u003Cbr> PEMS07(L) \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STFGNN | [Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16542) | [Mxnet](https:\u002F\u002Fgithub.com\u002FMengzhangLI\u002FSTFGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMengzhangLI\u002FSTFGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMengzhangLI\u002FSTFGNN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | BJ Taxi \u003Cbr> NYC Taxi \u003Cbr> NYC Bike1 \u003Cbr> NYC Bike2 | STGDN | [Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17761) | [Mxnet](https:\u002F\u002Fgithub.com\u002Fnimingniming\u002Fgdn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnimingniming\u002Fgdn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnimingniming\u002Fgdn?color=critical&style=social) | AAAI\u003Cbr>2021\n| Traffic Flow | SG-TAXI | TrGNN | [Traffic Flow Prediction with Vehicle Trajectories](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16104) | [Code](https:\u002F\u002Fgithub.com\u002Fmingqian000\u002FTrGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmingqian000\u002FTrGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmingqian000\u002FTrGNN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | Road \u003Cbr> POIs \u003Cbr> SIGtraf | DMLM | [Predicting Traffic Congestion Evolution: A Deep Meta Learning Approach](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0417.pdf) | [Future](https:\u002F\u002Fgithub.com\u002FHelenaYD\u002FDMLM) | IJCAI\u003Cbr>2021\n| Multivariat | East Bay \u003Cbr> METR-LA \u003Cbr> US | D-DA-GRNN | [EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458855) | [Code](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002FEnhanceNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frazvanc92\u002FEnhanceNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frazvanc92\u002FEnhanceNet?color=critical&style=social) | ICDE 2021\n| Multivariat | Water \u003Cbr> Humidity \u003Cbr> Wind, etc | EA-DRL | [An Actor-Critic Ensemble Aggregation Model for Time-Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458798) | None | ICDE 2021\n| Traffic Flow | TaxiBJ \u003Cbr> DiDiCD \u003Cbr> TaxiRome | AttConvLSTM | [Modeling Citywide Crowd Flows using Attentive Convolutional LSTM](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458664) | None | ICDE 2021\n| Traffic Speed \u003Cbr> Traffic Flow | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> eMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08...| Benchmark | [An Empirical Experiment on Deep Learning Models for Predicting Traffic Data](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458663) | [Future](https:\u002F\u002Fgithub.com\u002FHyunWookL\u002FAn-Empirical-Experiment-on-Deep-Learning-Models-for-Predicting-Traffic-Data) | ICDE 2021\n| Multivariat | Motes \u003Cbr> Soil \u003Cbr> Revenue \u003Cbr> Traffic \u003Cbr> 20CR | NET | [Network of Tensor Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3449969) | [Code](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FNET3) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbaoyujing\u002FNET3?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbaoyujing\u002FNET3?color=critical&style=social) | WWW 2021\n| Multivariat | VevoMusic \u003Cbr> WikiTraffic \u003Cbr> LOS-LOOP \u003Cbr> SZ-taxi | Radflow | [Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3449945) | [Code](https:\u002F\u002Fgithub.com\u002Falasdairtran\u002Fradflow) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falasdairtran\u002Fradflow?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falasdairtran\u002Fradflow?color=critical&style=social) | WWW 2021\n| Multivariat | METR-LA \u003Cbr> Wiki-EN | REST | [REST: Reciprocal Framework for Spatiotemporal-coupled Predictions](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3449928) | None | WWW 2021\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> HZMetro | ASTGNN | [Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9346058) | [Code](https:\u002F\u002Fgithub.com\u002FguoshnBJTU\u002FASTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FguoshnBJTU\u002FASTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FguoshnBJTU\u002FASTGNN?color=critical&style=social) | TKDE 2021\n| Multivariat | TaxiBJ \u003Cbr> BikeNYC-I \u003Cbr> BikeNYC-II \u003Cbr> TaxiNYC \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07(M) | DL-Traff | [DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482000) | Graph:[Code](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FDL-Traff-Graph) \u003Cbr> Grid:[TF](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FDL-Traff-Grid) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa20\u002FDL-Traff-Graph?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa20\u002FDL-Traff-Graph?color=critical&style=social) | CIKM\u003Cbr>2021\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07(M) | TorchGeoTem | [Code Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482000) | [Code](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002FCode_geometric_temporal) | CIKM\u003Cbr>2021\n| Traffic Flow | TaxiBJ \u003Cbr> BikeNYC | LLF | [Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482271) | None | CIKM\u003Cbr>2021\n| Multivariat | ETT \u003Cbr> Electricity | HI | [Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482120) | None | CIKM\u003Cbr>2021\n| Multivariat | ETT \u003Cbr> ELE | AGCNT | [AGCNT: Adaptive Graph Convolutional Network for Transformer-based Long Sequence Time-Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482054) | None | CIKM\u003Cbr>2021\n| Cellular Traffic | cellular | MPGAT | [Multivariate and Propagation Graph Attention Network for Spatial-Temporal Prediction with Outdoor Cellular Traffic](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482152) | [Code](https:\u002F\u002Fgithub.com\u002Fcylin-cmlab\u002FMPNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcylin-cmlab\u002FMPNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcylin-cmlab\u002FMPNet?color=critical&style=social) \u003Cbr> Future | CIKM\u003Cbr>2021\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> Simulated | STNN | [Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679008\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fsongyangco\u002FSTNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsongyangco\u002FSTNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsongyangco\u002FSTNN?color=critical&style=social) | ICDM 2021\n| Traffic Speed | DiDiCD \u003Cbr> DiDiXiAn | T-wave | [Trajectory WaveNet: A Trajectory-Based Model for Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679147) | [Code](https:\u002F\u002Fgithub.com\u002Fsongyangco\u002FSTNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsongyangco\u002FSTNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsongyangco\u002FSTNN?color=critical&style=social) | ICDM 2021\n| Multivariat | Sanyo \u003Cbr> Hanergy \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Exchange | SSDNet | [SSDNet: State Space Decomposition Neural Network for Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679135\u002F) | [Code](https:\u002F\u002Fgithub.com\u002FYangLIN1997\u002FSSDNet-ICDM2021) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYangLIN1997\u002FSSDNet-ICDM2021?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYangLIN1997\u002FSSDNet-ICDM2021?color=critical&style=social) | ICDM 2021\n| Traffic Volumn | HangZhou City \u003Cbr> JiNan City | CTVI | [Temporal Multi-view Graph Convolutional Networks for Citywide Traffic Volume Inference](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679045\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fdsj96\u002FCTVI-master) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdsj96\u002FCTVI-master?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdsj96\u002FCTVI-master?color=critical&style=social) | ICDM 2021\n| Traffic Volumn | Uber Movements \u003Cbr> Grab-Posisi | TEST-GCN | [TEST-GCN: Topologically Enhanced Spatial-Temporal Graph Convolutional Networks for Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679077) | None | ICDM 2021\n| Multivariat | Air Quality City \u003Cbr> Meterology | ATGCN | [Modeling Inter-station Relationships with Attentive Temporal Graph Convolutional Network for Air Quality Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441731) | None | WSDM 2021\n| Traffic Flow | WalkWLA \u003Cbr> BikeNYC \u003Cbr> TaxiNYC | PDSTN | [Predicting Crowd Flows via Pyramid Dilated Deeper Spatial-temporal Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441785) | None | WSDM 2021\n| Traffic Flow | PEMS04 \u003Cbr> PEMS08 | AGCRN | [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fce1aad92b939420fc17005e5461e6f48-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002FLeiBAI\u002FAGCRN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLeiBAI\u002FAGCRN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLeiBAI\u002FAGCRN?color=critical&style=social) | NeurIPS 2020\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> Wind \u003Cbr> Solar \u003Cbr> M4-Hourly | AST | [Adversarial Sparse Transformer for Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fc6b8c8d762da15fa8dbbdfb6baf9e260-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhihihihiwsf\u002FAST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhihihihiwsf\u002FAST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhihihihiwsf\u002FAST?color=critical&style=social) | NeurIPS 2020\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07 \u003Cbr> PEMS03 \u003Cbr> PEMS04 ,etc | StemGNN | [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fcdf6581cb7aca4b7e19ef136c6e601a5-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FStemGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmicrosoft\u002FStemGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmicrosoft\u002FStemGNN?color=critical&style=social) | NeurIPS 2020\n| Multivariat | M4 \u003Cbr> M3 \u003Cbr> Tourism | N-BEATS | [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1ecqn4YwB) | [Code+Keras](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002Fn-beats) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fphilipperemy\u002Fn-beats?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fphilipperemy\u002Fn-beats?color=critical&style=social) | ICLR\u003Cbr>2020\n| Traffic Flow | Traffic \u003Cbr> Energy \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | MTGNN | [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403118) | [Code](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FMTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnnzhan\u002FMTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnnzhan\u002FMTGNN?color=critical&style=social) | KDD\u003Cbr>2020\n| Traffic Flow | Taxi-NYC \u003Cbr> Bike-NYC \u003Cbr> CTM | DSAN | [Preserving Dynamic Attention for Long-Term Spatial-Temporal Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403118) | [TF](https:\u002F\u002Fgithub.com\u002Fhaoxingl\u002FDSAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhaoxingl\u002FDSAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhaoxingl\u002FDSAN?color=critical&style=social) | KDD\u003Cbr>2020\n| Traffic Speed \u003Cbr> Traffic Flow | Shenzhen | Curb-GAN | [Curb-GAN: Conditional Urban Traffic Estimation through Spatio-Temporal Generative Adversarial Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403127) | [Code](https:\u002F\u002Fgithub.com\u002FCurb-GAN\u002FCurb-GAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCurb-GAN\u002FCurb-GAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCurb-GAN\u002FCurb-GAN?color=critical&style=social) | KDD\u003Cbr>2020\n| Traffic Flow | TaxiBJ \u003Cbr> CrowdBJ \u003Cbr> TaxiJN \u003Cbr> TaxiGY | AutoST | [AutoST: Efficient Neural Architecture Search for Spatio-Temporal Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403122) | None | KDD\u003Cbr>2020\n| Traffic Volumn | W3-715 \u003Cbr> E5-2907 | HSTGCN | [Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403358) | None | KDD\u003Cbr>2020\n| Multivariat| Xiamen \u003Cbr> PEMS-BAY | GMAN | [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5477) | [TF](https:\u002F\u002Fgithub.com\u002Fzhengchuanpan\u002FGMAN)\u003Cbr> \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhengchuanpan\u002FGMAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhengchuanpan\u002FGMAN?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002FVincLee8188\u002FGMAN-Code) | AAAI\u003Cbr>2020\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STSGCN | [Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5438) | [Mxnet](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FSTSGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDavidham3\u002FSTSGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDavidham3\u002FSTSGCN?color=critical&style=social) \u003Cbr> [Code](https:\u002F\u002Fgithub.com\u002FSmallNana\u002FSTSGCN_Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSmallNana\u002FSTSGCN_Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSmallNana\u002FSTSGCN_Code?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | Traffic \u003Cbr> Energy \u003Cbr> NASDAQ | MLCNN | [Towards Better Forecasting by Fusing Near and Distant Future Visions](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5466) | [Code](https:\u002F\u002Fgithub.com\u002FsmallGum\u002FMLCNN-Multivariate-Time-Series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FsmallGum\u002FMLCNN-Multivariate-Time-Series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FsmallGum\u002FMLCNN-Multivariate-Time-Series?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | PEMS-S \u003Cbr> PEMS-BAY \u003Cbr> METR-LA \u003Cbr> BJF \u003Cbr> BRF \u003Cbr> BRF-L | SLCNN | [Spatio-temporal graph structure learning for traffic forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5770) | None | AAAI\u003Cbr>2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | MRA-BGCN | [Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5758) | None | AAAI\u003Cbr>2020\n| Metro Flow | HKMetro | WDGTC | [Tensor Completion for Weakly-Dependent Data on Graph for Metro Passenger Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5915) | [TF](https:\u002F\u002Fgithub.com\u002Fbonaldli\u002FWDG_TC) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbonaldli\u002FWDG_TC?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbonaldli\u002FWDG_TC?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | MovingMNIST \u003Cbr> TaxiBJ \u003Cbr> KTH | SA-ConvLSTM | [Self-Attention ConvLSTM for Spatiotemporal Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6819) | [TF](https:\u002F\u002Fgithub.com\u002FMahatmaSun1\u002FSaConvSLTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMahatmaSun1\u002FSaConvSLTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMahatmaSun1\u002FSaConvSLTM?color=critical&style=social) \u003Cbr> [Code](https:\u002F\u002Fgithub.com\u002Fjerrywn121\u002FTianChi_AIEarth) | AAAI\u003Cbr>2020\n| Metro Flow | SydneyMetro | MLC-PPF | [Potential Passenger Flow Prediction-A Novel Study for Urban Transportation Development](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5819) | None | AAAI\u003Cbr>2020\n| Commuting Flow | Lodes \u003Cbr> Pluto \u003Cbr> OSRM | GMEL | [Learning Geo-Contextual Embeddings for Commuting Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5425) | [Code](https:\u002F\u002Fgithub.com\u002Fjackmiemie\u002FGMEL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjackmiemie\u002FGMEL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjackmiemie\u002FGMEL?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | Traffic \u003Cbr> Exchange \u003Cbr> Solar | DeepTrends | [Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5496) | [TF](https:\u002F\u002Fgithub.com\u002FDerronXu\u002FDeepTrends) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDerronXu\u002FDeepTrends?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDerronXu\u002FDeepTrends?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | Traffic \u003Cbr> Electricity \u003Cbr> SmokeVideo \u003Cbr> PCSales \u003Cbr> RawMaterials | BHT | [Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6032) | [Python](https:\u002F\u002Fgithub.com\u002Fhuawei-noah\u002FBHT-ARIMA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuawei-noah\u002FBHT-ARIMA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuawei-noah\u002FBHT-ARIMA?color=critical&style=social) | AAAI\u003Cbr>2020\n| Traffic Speed | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | LSGCN | [LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.5555\u002F3491440.3491766) | [TF](https:\u002F\u002Fgithub.com\u002Fhelanzhu\u002FLSGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhelanzhu\u002FLSGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhelanzhu\u002FLSGCN?color=critical&style=social) | IJCAI\u003Cbr>2020\n| Traffic Flow | BikeNYC \u003Cbr> MobileBJ | CSCNet | [A Sequential Convolution Network for Population Flow Prediction with Explicitly Correlation Modelling](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.5555\u002F3491440.3491625) | None | IJCAI\u003Cbr>2020\n| Multivariat | USDCNY \u003Cbr> USDKRW \u003Cbr> USDIDR | WATTNet | [WATTNet: learning to trade FX via hierarchical spatio-temporal representation of highly multivariate time series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0630.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Fpablovicente\u002Fkeras-wattnet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpablovicente\u002Fkeras-wattnet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpablovicente\u002Fkeras-wattnet?color=critical&style=social) | IJCAI\u003Cbr>2020\n| Fine-grained | CitiBikeNYC \u003Cbr> Div \u003Cbr> Metro | GACNN | [Towards Fine-grained Flow Forecasting: A Graph Attention Approach for Bike Sharing Systems](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380097) | None | WWW 2020\n| Flow \u003Cbr> Distribution | Austin \u003Cbr> Louisville \u003Cbr> Minneapolis | GCScoot | [Dynamic Flow Distribution Prediction for Urban Dockless E-Scooter Sharing Reconfiguration](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380101) | None | WWW 2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | STGNN | [Traffic Flow Prediction via Spatial Temporal Graph Neural Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380186) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FSTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FSTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FSTGNN?color=critical&style=social) | WWW 2020\n| Traffic Speed | DiDiCD | STAG-GCN | [Spatiotemporal Adaptive Gated Graph Convolution Network for Urban Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411894) | [Code](https:\u002F\u002Fgithub.com\u002FRobinLu1209\u002FSTAG-GCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRobinLu1209\u002FSTAG-GCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRobinLu1209\u002FSTAG-GCN?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | ST-GRAT | [ST-GRAT: A Novel Spatio-temporal Graph Attention Networks for Accurately Forecasting Dynamically Changing Road Speed](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411940) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FST-GRAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FST-GRAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FST-GRAT?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Flow | BJ-Taxi \u003Cbr> NYC-Taxi \u003Cbr> NYC-Bike-1 \u003Cbr> NYC-Bike-2 | ST-CGA | [Spatial-Temporal Convolutional Graph Attention Networks for Citywide Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411941) | [Keras](https:\u002F\u002Fgithub.com\u002Fjbdj-star\u002Fcga) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjbdj-star\u002Fcga?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjbdj-star\u002Fcga?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Flow | NYCBike \u003Cbr> NYCTaxi | MT-ASTN | [Multi-task Adversarial Spatial-Temporal Networks for Crowd Flow Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3412054) | [Code](https:\u002F\u002Fgithub.com\u002FMiaoHaoSunny\u002FMT-ASTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMiaoHaoSunny\u002FMT-ASTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMiaoHaoSunny\u002FMT-ASTN?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Speed | SFO \u003Cbr> NYC | DIGC | [Deep Graph Convolutional Networks for Incident-Driven Traffic Speed Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411873) | None | CIKM\u003Cbr>2020\n| Metro Flow | SZMetro \u003Cbr> HZMetro | STP-TrellisNets | [STP-TrellisNets: Spatial-Temporal Parallel TrellisNets for Metro Station Passenger Flow Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411874) | None | CIKM\u003Cbr>2020\n| Multivariat | Air Quality \u003Cbr> BikeNYC \u003Cbr> METR-LA | AGSTN | [AGSTN: Learning Attention-adjusted Graph Spatio-Temporal Networks for Short-term Urban Sensor Value Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338255) | [Keras](https:\u002F\u002Fgithub.com\u002Fl852888\u002FAGSTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fl852888\u002FAGSTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fl852888\u002FAGSTN?color=critical&style=social) | ICDM 2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | FreqST | [FreqST: Exploiting Frequency Information in Spatiotemporal Modeling for Traffic Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338305) | None | ICDM 2020\n| Traffic Flow | PEMS03 \u003Cbr> PEMS07 | TSSRGCN | [Tssrgcn: Temporal spectral spatial retrieval graph convolutional network for traffic flow forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338393) | None | ICDM 2020\n| Multivariat | Air Quality \u003Cbr> DarkSky \u003Cbr> Geographic | DeepLATTE | [Building Autocorrelation-Aware Representations for Fine-Scale Spatiotemporal Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338402) | [Code](https:\u002F\u002Fgithub.com\u002Fspatial-computing\u002Fdeeplatte-fine-scale-prediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspatial-computing\u002Fdeeplatte-fine-scale-prediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fspatial-computing\u002Fdeeplatte-fine-scale-prediction?color=critical&style=social) | ICDM 2020\n| Traffic Flow | XATaxi \u003Cbr> BJTaxi \u003Cbr> PortoTaxi | ST-PEFs | [Interpretable Spatiotemporal Deep Learning Model for Traffic Flow Prediction Based on Potential Energy Fields](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338315) | None | ICDM 2020\n| Traffic Speed \u003Cbr> Flow | SZSpeed \u003Cbr> SZTaxi | cST-ML | [cST-ML: Continuous Spatial-Temporal Meta-Learning for Traffic Dynamics Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338315) | [Code](https:\u002F\u002Fgithub.com\u002Fyingxue-zhang\u002FcST-ML) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyingxue-zhang\u002FcST-ML?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyingxue-zhang\u002FcST-ML?color=critical&style=social) | ICDM 2020\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> PEMS07(M) | DeepGLO | [Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F3a0844cee4fcf57de0c71e9ad3035478-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Frajatsen91\u002Fdeepglo) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frajatsen91\u002Fdeepglo?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frajatsen91\u002Fdeepglo?color=critical&style=social) | NeurIPS 2019\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> Solar \u003Cbr> M4 \u003Cbr> Wind | LogSparse | [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F6775a0635c302542da2c32aa19d86be0-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fmlpotter\u002FTransformer_Time_Series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmlpotter\u002FTransformer_Time_Series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmlpotter\u002FTransformer_Time_Series?color=critical&style=social) | NeurIPS 2019\n| Multivariat | Synthetic \u003Cbr> ECG5000 \u003Cbr> Traffic | DILATE | [Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F466accbac9a66b805ba50e42ad715740-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fvincent-leguen\u002FDILATE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvincent-leguen\u002FDILATE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvincent-leguen\u002FDILATE?color=critical&style=social) | NeurIPS 2019\n| Traffic Flow | Earthquake | DeepUrbanEvent | [DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330996) | [Keras](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa\u002FDeepUrbanEvent) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa\u002FDeepUrbanEvent?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa\u002FDeepUrbanEvent?color=critical&style=social) | KDD\u003Cbr>2019\n| Traffic Flow \u003Cbr> Speed | TDrive \u003Cbr> METR-LA | ST-MetaNet | [Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330884) | [Mxnet](https:\u002F\u002Fgithub.com\u002Fpanzheyi\u002FST-MetaNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpanzheyi\u002FST-MetaNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpanzheyi\u002FST-MetaNet?color=critical&style=social) | KDD\u003Cbr>2019\n| Multivariat | Rossman \u003Cbr> Walmart \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Parts | ARU | [Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330996) | [TF](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002FARU) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpratham16cse\u002FARU?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpratham16cse\u002FARU?color=critical&style=social) | KDD\u003Cbr>2019\n| Multivariat | Air Quality | AccuAir | [AccuAir: Winning Solution to Air Quality Prediction for KDD Cup 2018](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330787) | None | KDD\u003Cbr>2019\n| Traffic Flow | Simulated \u003Cbr> RoadTraffic \u003Cbr> Wikipedia | ERMreg | [Regularized Regression for Hierarchical Forecasting Without Unbiasedness Conditions](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330976) | None | KDD\u003Cbr>2019\n| Multivariat \u003Cbr> under event | Climate \u003Cbr> Stock \u003Cbr> Pseudo | EVL | [Modeling Extreme Events in Time Series Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330896) |None | KDD\u003Cbr>2019\n| Traffic Flow | PEMS04 \u003Cbr> PEMS08 \u003Cbr> METR-LA | ASTGCN | [Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3881) | [Mxnet](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FASTGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDavidham3\u002FASTGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDavidham3\u002FASTGCN?color=critical&style=social) | AAAI\u003Cbr>2019\n| Traffic Flow \u003Cbr> Speed | NYC \u003Cbr> PEMS0(M) | DGCNN | [Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3877) | None | AAAI\u003Cbr>2019\n| Traffic FLow | NYC-Taxi \u003Cbr> NYC-Bike | STDN | [Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4511) | [Keras](https:\u002F\u002Fgithub.com\u002Ftangxianfeng\u002FSTDN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftangxianfeng\u002FSTDN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftangxianfeng\u002FSTDN?color=critical&style=social) | AAAI\u003Cbr>2019\n| Traffic Flow | MobileBJ \u003Cbr> BikeNYC | DeepSTN+ | [DeepSTN+: context-aware spatial-temporal neural network for crowd flow prediction in metropolis](https:\u002F\u002Fdoi.org\u002F10.1609\u002Faaai.v33i01.33011020) | [TF](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FDeepSTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FDeepSTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FDeepSTN?color=critical&style=social) | AAAI\u003Cbr>2019\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | Res-RGNN | [Gated residual recurrent graph neural networks for traffic prediction](https:\u002F\u002Fdoi.org\u002F10.1609\u002Faaai.v33i01.3301485) | None | AAAI\u003Cbr>2019\n| Traffic FLow | MetroBJ \u003Cbr> BusBJ \u003Cbr> TaxiBJ | GSTNet | [GSTNet: Global Spatial-Temporal Network for Traffic Flow Prediction](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0317.pdf) | [Code](https:\u002F\u002Fgithub.com\u002FWoodSugar\u002FGSTNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWoodSugar\u002FGSTNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWoodSugar\u002FGSTNet?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | GWN | [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2019\u002F264) | [Code](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FGraph-WaveNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnnzhan\u002FGraph-WaveNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnnzhan\u002FGraph-WaveNet?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Traffic Flow | DidiSY \u003Cbr> BikeNYC \u003Cbr> TaxiBJ | STG2Seq | [STG2Seq: Spatial-Temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Ein6fZbizNZ) | [TF](https:\u002F\u002Fgithub.com\u002FLeiBAI\u002FSTG2Seq) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLeiBAI\u002FSTG2Seq?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLeiBAI\u002FSTG2Seq?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Multivariat | GHL \u003Cbr> Electricity \u003Cbr>TEP | DyAt | [DyAt Nets: Dynamic Attention Networks for State Forecasting in Cyber-Physical Systems](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0441.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Fnmuralid1\u002FDynamicAttentionNetworks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Multivariat | Air Quality | MGED | [Multi-Group Encoder-Decoder Networks to Fuse Heterogeneous Data for Next-Day Air Quality Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0603.pdf) | None | IJCAI\u003Cbr>2019\n| Traffic Volumn | Chicago \u003Cbr> Boston | MetaST | [Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313577) | [TF](https:\u002F\u002Fgithub.com\u002Fhuaxiuyao\u002FMetaST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuaxiuyao\u002FMetaST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuaxiuyao\u002FMetaST?color=critical&style=social) | WWW 2019\n| TrafficPred \u003Cbr> imputation |GZSpeed \u003Cbr> HZMetro \u003Cbr> Seattle \u003Cbr> London | BTF | [Bayesian Temporal Factorization for Multidimensional Time Series Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9380704) | [Python](https:\u002F\u002Fgithub.com\u002Fnmuralid1\u002FDynamicAttentionNetworks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) | TPAMI 2019\n| Multivariat | Gas Station | DSANet | [DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3358132) | [Code](https:\u002F\u002Fgithub.com\u002Fbighuang624\u002FDSANet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbighuang624\u002FDSANet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbighuang624\u002FDSANet?color=critical&style=social) | CIKM\u003Cbr>2019\n| Multivariat | Solar \u003Cbr> Traffic \u003Cbr> Exchange \u003Cbr> Electricity \u003Cbr> PEMS ,etc | Study | [Experimental Study of Multivariate Time Series Forecasting Models](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357826) | None | CIKM\u003Cbr>2019\n| Traffic Speed | DiDiCD \u003Cbr> DiDiXA | BTRAC | [Boosted Trajectory Calibration for Traffic State Estimation](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970880) | None | ICDM 2019\n| Multivariat | Photovoltaic | MTEX-CNN | [MTEX-CNN: Multivariate Time Series EXplanations for Predictions with Convolutional Neural Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970899) | [Code](https:\u002F\u002Fgithub.com\u002Fduyanhpham-brs\u002FXAI-Multivariate-Time-Series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fduyanhpham-brs\u002FXAI-Multivariate-Time-Series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fduyanhpham-brs\u002FXAI-Multivariate-Time-Series?color=critical&style=social) | ICDM 2019\n| Traffic Speed | BJER4 \u003Cbr> PEMS07(M) \u003Cbr> PEMS07(L) | STGCN | [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=SkNeyVzOWB) | [TF](https:\u002F\u002Fgithub.com\u002FVeritasYin\u002FSTGCN_IJCAI-18) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVeritasYin\u002FSTGCN_IJCAI-18?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVeritasYin\u002FSTGCN_IJCAI-18?color=critical&style=social) [Mxnet](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FSTGCN) [Code1](https:\u002F\u002Fgithub.com\u002FFelixOpolka\u002FSTGCN-Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFelixOpolka\u002FSTGCN-Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFelixOpolka\u002FSTGCN-Code?color=critical&style=social) [Code2](https:\u002F\u002Fgithub.com\u002Fhazdzz\u002FSTGCN) [Code3](https:\u002F\u002Fgithub.com\u002FAguin\u002FSTGCN-Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAguin\u002FSTGCN-Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAguin\u002FSTGCN-Code?color=critical&style=social) | IJCAI\u003Cbr>2018\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | DCRNN | [Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=SJiHXGWAZ) | [TF](https:\u002F\u002Fgithub.com\u002Fliyaguang\u002FDCRNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliyaguang\u002FDCRNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliyaguang\u002FDCRNN?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002Fchnsh\u002FDCRNN_Code) |ICLR\u003Cbr>2018\n\n\n\n\n\n# [Multivariat Probabilistic Time Series Forecasting](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums:40+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| probability | Exchange \u003Cbr> ILI \u003Cbr> ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Weather | TMDM | [Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=qae04YACHs) | None | ICLR\u003Cbr>2024\n| probability | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wikipedia | VQ-TR | [VQ-TR: Vector Quantized Attention for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=IxpTsFS7mh) | None | ICLR\u003Cbr>2024\n| Conformer | COVID-19 | CopulaCPTS | [Copula Conformal prediction for multi-step time series prediction](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch54) | [Code](hhttps:\u002F\u002Fgithub.com\u002FRose-STL-Lab\u002FCopulaCPTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRose-STL-Lab\u002FCopulaCPTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRose-STL-Lab\u002FCopulaCPTS?color=critical&style=social) | ICLR\u003Cbr>2024 \n| probability | Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wikipedia | LDT | [ Latent Diffusion Transformer for Probabilistic Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29085) | None | AAAI\u003Cbr>2024\n| probability | Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Exchange \u003Cbr> M4-Hourly \u003Cbr> UberTLC \u003Cbr> KDDCup \u003Cbr> Wikipedia | TSDiff | [Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F5a1a10c2c2c9b9af1514687bc24b8f3d-Abstract-Conference.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Famazon-science\u002Funconditional-time-series-diffusion) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famazon-science\u002Funconditional-time-series-diffusion?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famazon-science\u002Funconditional-time-series-diffusion?color=critical&style=social) | NIPS\u003Cbr>2023\n| Quantile | Electricity \u003Cbr> Kaggle \u003Cbr> M4-daily \u003Cbr> Traffic \u003Cbr> Wiki | Ensemble | [Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fhasson23a.html) | None | ICML\u003Cbr>2023\n| Quantile | Boston \u003Cbr> Concrete \u003Cbr> kin8nm \u003Cbr> Power \u003Cbr> Protein \u003Cbr> Wine \u003Cbr> M5 | BVAE | [Neural Spline Search for Quantile Probabilistic Modeling](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26184) | None | AAAI\u003Cbr>2023\n| Quantile | Traffc \u003Cbr> Electricity \u003Cbr> Solar Energy | pTSE | [pTSE: A Multi-model Ensemble Method for Probabilistic Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F521) | None| IJCAI\u003Cbr>2023 \n| probability | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DeepSTUQ | [Uncertainty Quantification for Traffic Forecasting: A Unified Approach](https:\u002F\u002Fdoi.org\u002F10.1109\u002FICDE55515.2023.00081) | None| ICDE 2023 \n| probability | Electricity \u003Cbr> Traffc \u003Cbr> Solar \u003Cbr> Exchange \u003Cbr> M4 | PDTrans | [Probabilistic Decomposition Transformer for Time Series Forecasting](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch54) | [Code](hhttps:\u002F\u002Fgithub.com\u002FJL-tong\u002FPDTrans) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJL-tong\u002FPDTrans?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJL-tong\u002FPDTrans?color=critical&style=social) | SDM 2023 \n| probability | Taxi\u003Cbr> \u003Cbr> Electricity Traffc\u003Cbr> Exchange | COPDEEPAR | [Coherent Probabilistic Forecasting of Temporal Hierarchies](https:\u002F\u002Fproceedings.mlr.press\u002Fv206\u002Frangapuram23a.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluonts\u002Ftree\u002Fdev\u002Fsrc\u002Fgluonts\u002Fnursery\u002Ftemporal_hierarchical_forecasting\u002Fmodel) | AISTATS 2023 \n| probability | Traffic \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> ETT \u003Cbr> Wind | BVAE | [Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement](https:\u002F\u002Fopenreview.net\u002Fforum?id=rG0jm74xtx) | [Paddle](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FPaddleSpatial\u002Ftree\u002Fmain\u002Fresearch\u002FD3VAE) | NeurIPS 2022\n| probability & | Stock Price \u003Cbr> Wind Speed| Volat | [Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fbenton22a.html) | [Code,GCode](https:\u002F\u002Fgithub.com\u002Fg-benton\u002FVolt) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fg-benton\u002FVolt?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fg-benton\u002FVolt?color=critical&style=social) | ICML\u003Cbr>2022\n| probability & \u003Cbr> Point & \u003Cbr> Others | electricity \u003Cbr> Yacht \u003Cbr> Boston, etc | AQF | [Autoregressive Quantile Flows for Predictive Uncertainty Estimation](https:\u002F\u002Fopenreview.net\u002Fforum?id=z1-I6rOKv1S) | None | ICLR\u003Cbr>2022\n| probability | IRIS \u003Cbr> Digits \u003Cbr> EightSchools | EMF | [Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling](https:\u002F\u002Fopenreview.net\u002Fforum?id=9pEJSVfDbba) | [Code](https:\u002F\u002Fgithub.com\u002Fgisilvs\u002FEmbeddedModelFlows) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgisilvs\u002FEmbeddedModelFlows?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgisilvs\u002FEmbeddedModelFlows?color=critical&style=social) | ICLR\u003Cbr>2022\n| probability | Bike Sharing \u003Cbr> UCI \u003Cbr> NYU Depth v2 | NatPN | [Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions](https:\u002F\u002Fwww.in.tum.de\u002Fdaml\u002Fnatpn\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fborchero\u002Fnatural-posterior-network) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fborchero\u002Fnatural-posterior-network?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fborchero\u002Fnatural-posterior-network?color=critical&style=social) | ICLR\u003Cbr>2022\n| probability | Carbon \u003Cbr> Concrete \u003Cbr> Energy \u003Cbr> Housing,etc | β−NLL | [On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=aPOpXlnV1T) | [Code](https:\u002F\u002Fgithub.com\u002Fmartius-lab\u002Fbeta-nll) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmartius-lab\u002Fbeta-nll?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmartius-lab\u002Fbeta-nll?color=critical&style=social) | ICLR\u003Cbr>2022\n| probability & Point | CDP \u003Cbr> SLD | STZINB-GNN | [Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539093) | [Code](https:\u002F\u002Fgithub.com\u002FZhuangDingyi\u002FSTZINB) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhuangDingyi\u002FSTZINB?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZhuangDingyi\u002FSTZINB?color=critical&style=social) | KDD\u003Cbr>2022\n| probability & Point | Sichuan \u003Cbr> Panama | PrEF | [PrEF: Probabilistic Electricity Forecasting via Copula-Augmented State Space Model](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aisi7128) | None | AAAI\u003Cbr>2022\n| probability | ETT \u003Cbr> Solar \u003Cbr> Electricity | KLST | [Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F404) | [Code](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002FAggForecaster) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpratham16cse\u002FAggForecaster?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpratham16cse\u002FAggForecaster?color=critical&style=social) | IJCAI\u003Cbr>2022\n| probability | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Wiki | EMSSM | [Memory Augmented State Space Model for Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F479) | None | IJCAI\u003Cbr>2022\n| Prediction \u003Cbr> Intervals | DMV \u003Cbr> Census \u003Cbr> Forest \u003Cbr> Power | Evaluation | [Prediction Intervals for Learned Cardinality Estimation: An Experimental Evaluation](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F404) | None | ICDE 2022\n| Periodic Forecasting | ETT \u003Cbr> Weather | DeepFS | [Bridging Self-Attention and Time Series Decomposition for Periodic Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557077) | None | CIKM\u003Cbr>2022\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> M4 | ISQF | [Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv151\u002Fpark22a.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluonts\u002Fblob\u002F4fef7e26470d15096b11b005be846dedf87fb736\u002Fsrc\u002Fgluonts\u002Ftorch\u002Fdistributions\u002Fisqf.py) | AISTATS 2022\n| probability | M4 \u003Cbr> Traffic \u003Cbr> Electricity | Robust | [Robust Probabilistic Time Series Forecasting](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.11910) | [GluonTS](https:\u002F\u002Fgithub.com\u002Ftetrzim\u002Frobust-probabilistic-forecasting) | AISTATS 2022\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> M4 | MQF | [Multivariate Quantile Function Forecaster](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.11316.pdf) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluon-ts\u002Ftree\u002Fmaster\u002Fsrc\u002FGluonTS\u002Ftorch\u002Fmodel\u002Fmqf2) | AISTATS 2022\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> Azure | C2FAR | [C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=lHuPdoHBxbg) | [Future](https:\u002F\u002Fgithub.com\u002Fhuaweicloud\u002Fc2far_forecasting) | AISTATS 2022\n| Imputation & \u003Cbr> Probabilistic | PhysioNet \u003Cbr> Air Quality | CSDI | [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fcfe8504bda37b575c70ee1a8276f3486-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fermongroup\u002FCSDI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fermongroup\u002FCSDI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fermongroup\u002FCSDI?color=critical&style=social) | NeurIPS 2021\n| probability | MIMIC-III \u003Cbr> EEG \u003Cbr> COVID-19 | CF-RNN | [Conformal Time-series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F312f1ba2a72318edaaa995a67835fad5-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fkamilest\u002Fconformal-rnn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkamilest\u002Fconformal-rnn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkamilest\u002Fconformal-rnn?color=critical&style=social) | NeurIPS 2021\n| probability | CDC Flu | EPIFNP | [When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fa4a1108bbcc329a70efa93d7bf060914-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FEpiFNP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FEpiFNP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FEpiFNP?color=critical&style=social) | NeurIPS 2021\n| probability | Basketball \u003Cbr> Weather| GLIM | [Probability Paths and the Structure of Predictions over Time](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F7f53f8c6c730af6aeb52e66eb74d8507-Abstract.html) | [R](https:\u002F\u002Fgithub.com\u002FItsMrLin\u002Fprobability-paths) | NeurIPS 2021\n| probability | Facebook \u003Cbr> Meps \u003Cbr> Star \u003Cbr> Bike ,etc | LSF | [Probabilistic Forecasting: A Level-Set Approach](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F32b127307a606effdcc8e51f60a45922-Abstract.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluon-ts\u002Ftree\u002Fmaster\u002Fsrc\u002FGluonTS\u002Fmodel\u002Frotbaum) | NeurIPS 2021\n| probability | Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wikipedia | ProTran | [Probabilistic Transformer For Time Series Analysis](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fc68bd9055776bf38d8fc43c0ed283678-Abstract.html) | None | NeurIPS 2021\n| Prediction \u003Cbr> Intervals | Solar \u003Cbr> Wind | EnbPI | [Conformal prediction interval for dynamic time-series](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fxu21h.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhamrel-cxu\u002FEnbPI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhamrel-cxu\u002FEnbPI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhamrel-cxu\u002FEnbPI?color=critical&style=social) | ICML\u003Cbr>2021\n| probability | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wiki | TimeGrad | [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Frasul21a.html) | [Code](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002FCode-ts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) | ICML\u003Cbr>2021\n| probability & Point | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> Electricity \u003Cbr> Traffic , etc | AGCGRU | [RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fpal21b.html) | [TF](https:\u002F\u002Fgithub.com\u002Fnetworkslab\u002Frnn_flow) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnetworkslab\u002Frnn_flow?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnetworkslab\u002Frnn_flow?color=critical&style=social) | ICML\u003Cbr>2021\n| probability | Tourism \u003Cbr> Labour \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> Electricity \u003Cbr> Traffic , etc | Hier-E2E | [End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Frangapuram21a.html) | [MXNet](https:\u002F\u002Fgithub.com\u002Frshyamsundar\u002FGluonTS-hierarchical-ICML-2021) | ICML\u003Cbr>2021\n| probability | Sine \u003Cbr> MNIST \u003Cbr> Billiards \u003Cbr> S&P \u003Cbr> Stock | Whittle | [Whittle Networks: A Deep Likelihood Model for Time Series](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fyu21c.html) | [TF](https:\u002F\u002Fgithub.com\u002Fml-research\u002FWhittleNetworks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fml-research\u002FWhittleNetworks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fml-research\u002FWhittleNetworks?color=critical&style=social) | ICML\u003Cbr>2021\n| probability | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PMU | GTS | [Discrete Graph Structure Learning for Forecasting Multiple Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=WEHSlH5mOk) | [Code](https:\u002F\u002Fgithub.com\u002Fchaoshangcs\u002FGTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchaoshangcs\u002FGTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchaoshangcs\u002FGTS?color=critical&style=social) | ICLR\u003Cbr>2021\n| probability & Point| Exchange \u003Cbr>Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wikipedia | MAF | [Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows](https:\u002F\u002Fopenreview.net\u002Fforum?id=WiGQBFuVRv) | [Code](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002FCode-ts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) | ICLR\u003Cbr>2021\n| probability | MNIST \u003Cbr> PhysioNet2012 | PNCNN | [Probabilistic Numeric Convolutional Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=T1XmO8ScKim) | None | ICLR\u003Cbr>2021\n| probability & Point | Energy \u003Cbr> Wine \u003Cbr> Power \u003Cbr> MSD, etc | PGBM | [Probabilistic Gradient Boosting Machines for Large-Scale Probabilistic Regression](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467278) | [Code](https:\u002F\u002Fgithub.com\u002Felephaint\u002Fpgbm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Felephaint\u002Fpgbm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Felephaint\u002Fpgbm?color=critical&style=social) | KDD\u003Cbr>2021\n| probability | DiDICD | TrajNet | [TrajNet: A Trajectory-Based Deep Learning Model for Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467236) | None | KDD\u003Cbr>2021\n| probability | Air Quality \u003Cbr> METR-LA \u003Cbr> COVID-19 | UQ | [Quantifying Uncertainty in Deep Spatiotemporal Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467325) | [Code](https:\u002F\u002Fgithub.com\u002FDongxiaW\u002FQuantifying_Uncertainty_in_Deep_Spatiotemporal_Forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDongxiaW\u002FQuantifying_Uncertainty_in_Deep_Spatiotemporal_Forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDongxiaW\u002FQuantifying_Uncertainty_in_Deep_Spatiotemporal_Forecasting?color=critical&style=social) | KDD\u003Cbr>2021\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> Environment \u003Cbr> Air Quality \u003Cbr> Dewpoint,etc| VSMHN | [Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17023) | [Code](https:\u002F\u002Fgithub.com\u002Flongyuanli\u002FVSMHN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flongyuanli\u002FVSMHN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flongyuanli\u002FVSMHN?color=critical&style=social) | AAAI\u003Cbr>2021\n| probability & Point | Traffic \u003Cbr> Electricity \u003Cbr> Wiki \u003Cbr> Solar \u003Cbr> Taxi | TLAE | [Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17101) | None | AAAI\u003Cbr>2021\n| probability | Patient EHR \u003Cbr> Public Health | UNITE | [UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450087) | [Code](https:\u002F\u002Fgithub.com\u002FChacha-Chen\u002FUNITE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChacha-Chen\u002FUNITE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FChacha-Chen\u002FUNITE?color=critical&style=social) | WWW 2021\n| probability | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Wiki | ARSGLS | [Deep Rao-Blackwellised Particle Filters for Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fafb0b97df87090596ae7c503f60bb23f-Abstract.html) | None | NeurIPS 2020\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> Wind \u003Cbr> Solar \u003Cbr> M4 | AST | [Adversarial Sparse Transformer for Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fc6b8c8d762da15fa8dbbdfb6baf9e260-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhihihihiwsf\u002FAST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhihihihiwsf\u002FAST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhihihihiwsf\u002FAST?color=critical&style=social) | NeurIPS 2020\n| probability | Traffic \u003Cbr> Electricity | STRIPE | [Probabilistic Time Series Forecasting with Shape and Temporal Diversity](https:\u002F\u002Fpapers.NeurIPS.cc\u002Fpaper\u002F2020\u002Fhash\u002F2f2b265625d76a6704b08093c652fd79-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fvincent-leguen\u002FSTRIPE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvincent-leguen\u002FSTRIPE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvincent-leguen\u002FSTRIPE?color=critical&style=social) | NeurIPS 2020\n| probability | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Wiki \u003Cbr> Traffic | NKF | [Normalizing Kalman Filters for Multivariate Time Series Analysis](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F1f47cef5e38c952f94c5d61726027439-Abstract.html) | None | NeurIPS 2020\n| quantile | MIMIC-III | BJRNN | [Frequentist Uncertainty in RNNs via Blockwise Influence Functions](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Falaa20b.html) | [Code](https:\u002F\u002Fgithub.com\u002Fahmedmalaa\u002Frnn-blockwise-jackknife) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fahmedmalaa\u002Frnn-blockwise-jackknife?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fahmedmalaa\u002Frnn-blockwise-jackknife?color=critical&style=social) | ICML\u003Cbr>2020\n| probability | S&P 500 \u003Cbr> Electricity | Monte-Carlo | [Adversarial Attacks on Probabilistic Autoregressive Forecasting Models](https:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fdang-nhu20a.html) | [Code](https:\u002F\u002Fgithub.com\u002Feth-sri\u002Fprobabilistic-forecasts-attacks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Feth-sri\u002Fprobabilistic-forecasts-attacks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Feth-sri\u002Fprobabilistic-forecasts-attacks?color=critical&style=social) | ICML\u003Cbr>2020\n| probability | Boston \u003Cbr> Concrete \u003Cbr>Energy \u003Cbr> Kin8nm \u003Cbr> Naval, etc | NGBoost | [NGBoost: Natural Gradient Boosting for Probabilistic Prediction](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fduan20a.html) | [Python](https:\u002F\u002Fgithub.com\u002Fstanfordmlgroup\u002Fngboost) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fstanfordmlgroup\u002Fngboost?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fstanfordmlgroup\u002Fngboost?color=critical&style=social) | ICML\u003Cbr>2020\n| probability | Physionet \u003Cbr> NHIS | DME | [Deep Mixed Effect Model Using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5773) | [Code](https:\u002F\u002Fgithub.com\u002Fjik0730\u002FDeep-Mixed-Effect-Model-using-Gaussian-Processes) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjik0730\u002FDeep-Mixed-Effect-Model-using-Gaussian-Processes?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjik0730\u002FDeep-Mixed-Effect-Model-using-Gaussian-Processes?color=critical&style=social) | AAAI\u003Cbr>2020\n| probability | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> NYCTaxi \u003Cbr> Wikipedia | copula | [High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F0b105cf1504c4e241fcc6d519ea962fb-Abstract.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release) | NeurIPS 2019\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> NYCTaxi \u003Cbr> Uber | DF | [Deep Factors for Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fwang19k.html) | None | ICML\u003Cbr>2019\n| probability | Weather | DUQ | [Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330704) | [Keras](https:\u002F\u002Fgithub.com\u002FBruceBinBoxing\u002FDeep_Learning_Weather_Forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBruceBinBoxing\u002FDeep_Learning_Weather_Forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBruceBinBoxing\u002FDeep_Learning_Weather_Forecasting?color=critical&style=social) | KDD\u003Cbr>2019\n| probability | JD50K | framework | [Multi-Horizon Time Series Forecasting with Temporal Attention Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330662) | None | KDD\u003Cbr>2019\n| probability | MIMIC-III | TPF | [Temporal Probabilistic Profiles for Sepsis Prediction in the ICU](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330747) | None | KDD\u003Cbr>2019\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> Dom | SQF | [Probabilistic Forecasting with Spline Quantile Function RNNs](https:\u002F\u002Fproceedings.mlr.press\u002Fv89\u002Fgasthaus19a.html) | None | AISTATS 2019\n| probability | More | More | [https:\u002F\u002Fgithub.com\u002Fzzw-zwzhang\u002FAwesome-of-Time-Series-Prediction](https:\u002F\u002Fgithub.com\u002Fzzw-zwzhang\u002FAwesome-of-Time-Series-Prediction) | More | \n\n\n\n\u003C!--\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> Dom | SQF | [Probabilistic Forecasting with Spline Quantile Function RNNs](https:\u002F\u002Fproceedings.mlr.press\u002Fv89\u002Fgasthaus19a.html) | None | AISTATS 2019 \n\n| probability | Electricity \u003Cbr> Traffic \u003Cbr> NYCTaxi \u003Cbr> Uber | framework | [Multi-Horizon Time Series Forecasting with Temporal Attention Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330662) | [Code](https:\u002F\u002Fgithub.com\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release?color=critical&style=social) | KDD\u003Cbr>2019 -->\n\n\n\n# [Time Series Imputation](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums: 30+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| ImputeFormer | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS03478 \u003Cbr> Solar \u003Cbr> CER-EN \u003Cbr> AQI | ImputeFormer | [ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671751) | [Code](https:\u002F\u002Fgithub.com\u002Ftongnie\u002FImputeFormer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftongnie\u002FImputeFormer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftongnie\u002FImputeFormer?color=critical&style=social) | KDD\u003Cbr>2024\n| Imputation | AirQuality \u003Cbr> Stocks \u003Cbr> Electricity \u003Cbr> Energy | CTA | [Continuous-time Autoencoders for Regular and Irregular Time Series Imputation](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fchen23f.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhyowonwi\u002FCTA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhyowonwi\u002FCTA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhyowonwi\u002FCTA?color=critical&style=social) | WSDM 2024\n| Imputation | PM2.5 \u003Cbr> PhysioNet | CSBI | [Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fchen23f.html) | [Code](https:\u002F\u002Fgithub.com\u002Fmorganstanley\u002FMSML) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmorganstanley\u002FMSML?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmorganstanley\u002FMSML?color=critical&style=social) | ICML\u003Cbr>2023\n| Imputation | MIMIC-III \u003Cbr> PhysioNet | MNAR | [Probabilistic Imputation for Time-series Classification with Missing Data](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fkim23m.html) | [TF](https:\u002F\u002Fgithub.com\u002Fyuneg11\u002FSupNotMIWAE-with-ObsDropout) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuneg11\u002FSupNotMIWAE-with-ObsDropout?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuneg11\u002FSupNotMIWAE-with-ObsDropout?color=critical&style=social) | ICML\u003Cbr>2023\n| Imputation | Guangzhou \u003Cbr> Solar-energy\u003Cbr> Westminster | TIDER \u003Cbr>(EncDec,AR) | [Multivariate Time-series Imputation with Disentangled Temporal Representations](https:\u002F\u002Fopenreview.net\u002Fforum?id=rdjeCNUS6TG) | [Code](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002FTIDER-527C\u002Freadme.md) | ICLR\u003Cbr>2023\n| Imputation | COVID-19 \u003Cbr> AQ36 \u003Cbr> PeMS-BA \u003Cbr> PeMS-LA \u003Cbr> PeMS-SD| PoGeVon | [Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3580305.3599444) | [Author](https:\u002F\u002Fgithub.com\u002FDerek-Wds) | KDD\u003Cbr>2023\n| Imputation | PhysioNet \u003Cbr> Human Activity | Warpformer | [Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599543) | [Code](https:\u002F\u002Fgithub.com\u002FimJiawen\u002FWarpformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FimJiawen\u002FWarpformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FimJiawen\u002FWarpformer?color=critical&style=social) | KDD\u003Cbr>2023\n| Imputation | Air Quality \u003Cbr> METR-LA\u003Cbr> PEMS-BAY | PriSTI | [PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.09746) | [Code](https:\u002F\u002Fgithub.com\u002FLMZZML\u002FPriSTI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMZZML\u002FPriSTI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMZZML\u002FPriSTI?color=critical&style=social) | ICDE 2023\n| Imputation | PhysioNet12 \u003Cbr> PhysioNet19 \u003Cbr> MIMIC-III | DA-TASWDM | [Density-Aware Temporal Attentive Step-wise Diffusion Model For Medical Time Series Imputation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614840) | None | CIKM\u003Cbr>2023\n| Imputation | TEDDY \u003Cbr> CAMELS | TSEst | [Attention-Based Multi-modal Missing Value Imputation for Time Series Data with High Missing Rate](hhttps:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch53) | [Code](https:\u002F\u002Fgithub.com\u002Fcompbiolabucf\u002FTSEst) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcompbiolabucf\u002FTSEst?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcompbiolabucf\u002FTSEst?color=critical&style=social) | SDM 2023\n| Imputation | Air Quality \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> CER-E | GRIN \u003Cbr>(EncDec,AR) | [Filling the G_ap_s-Multivariate Time Series Imputation by Graph Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=kOu3-S3wJ7) | [Code](https:\u002F\u002Fgithub.com\u002FGraph-Machine-Learning-Group\u002Fgrin) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-Machine-Learning-Group\u002Fgrin?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-Machine-Learning-Group\u002Fgrin?color=critical&style=social) | ICLR\u003Cbr>2022\n| Imputation | PhysioNet \u003Cbr> MIMIC-III \u003Cbr> Climate | HeTVAE \u003Cbr>(Attn,VAE) | [Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=Az7opqbQE-3) | [Code](https:\u002F\u002Fgithub.com\u002Freml-lab\u002Fhetvae) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Freml-lab\u002Fhetvae?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Freml-lab\u002Fhetvae?color=critical&style=social) | ICLR\u003Cbr>2022\n| Imputation | MIMIC-III \u003Cbr> OPHTHALMIC \u003Cbr> MNIST Physionet \u003Cbr> | GIL \u003Cbr>(AR,Attn, \u003Cbr> GRADIENT LEARNING) | [Gradient Importance Learning for Incomplete Observations](https:\u002F\u002Fopenreview.net\u002Fforum?id=fXHl76nO2AZ) | [TF](https:\u002F\u002Fgithub.com\u002Fgaoqitong\u002Fgradient-importance-learning) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgaoqitong\u002Fgradient-importance-learning?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgaoqitong\u002Fgradient-importance-learning?color=critical&style=social) | ICLR\u003Cbr>2022\n| Imputation | Chlorine level \u003Cbr> SML2010 \u003Cbr> Air Quality | D-NLMC | [Dynamic Nonlinear Matrix Completion for Time-Varying Data Imputation](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai12088) | [Matlab](https:\u002F\u002Fgithub.com\u002Fjicongfan) \u003Cbr> Author \u003Cbr> Github | AAAI\u003Cbr>2022\n| Imputation | COMPAS \u003Cbr> Adult \u003Cbr> HSLS | ME | [Online Missing Value Imputation and Change Point Detection with the Gaussian Copula](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai6237) | [gcimpute](https:\u002F\u002Fgithub.com\u002Fyuxuanzhao2295\u002FOnline-Missing-Value-Imputation-and-Change-Point-Detection-with-the-Gaussian-Copula) | AAAI\u003Cbr>2022\n| Imputation | Fair MIP Forest | | [Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F21189) | None | AAAI\u003Cbr>2022\n| Imputation | Chengdu \u003Cbr> New York | STCPA | [Traffic Speed Imputation with Spatio-Temporal Attentions and Cycle-Perceptual Training](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557480) | [Code](https:\u002F\u002Fgithub.com\u002FSam1224\u002FSTCPA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSam1224\u002FSTCPA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSam1224\u002FSTCPA?color=critical&style=social) | CIKM\u003Cbr>2022\n| Imputation | Nanjingyby \u003Cbr> PEMS08 | AST-CMCN | [Generative-Free Urban Flow Imputation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557334) | SenzhangWang | CIKM\u003Cbr>2022\n| Imputation | Foursquare \u003Cbr> Gowalla | MDI-MG | [Multi-task Generative Adversarial Network for Missing Mobility Data Imputation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557654) | None | CIKM\u003Cbr>2022\n| Imputation | Self-defined | MACRO | [Multi-Graph Convolutional Recurrent Network for Fine-Grained Lane-Level Traffic Flow Imputation](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027759) | [Code](https:\u002F\u002Fgithub.com\u002FJingci\u002FMACRO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJingci\u002FMACRO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJingci\u002FMACRO?color=critical&style=social) | ICDM 2022\n| Imputation | Physionet \u003Cbr> MIMIC-III \u003Cbr> Human Activity | mTAND | [Multi-Time Attention Networks for Irregularly Sampled Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=4c0J6lwQ4_) | [Code](https:\u002F\u002Fgithub.com\u002Freml-lab\u002FmTAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Freml-lab\u002FmTAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Freml-lab\u002FmTAN?color=critical&style=social) | ICLR\u003Cbr>2021\n| Imputation | METR-LA \u003Cbr> NREL \u003Cbr> USHCN \u003Cbr> SeData | IGNNK | [Inductive Graph Neural Networks for Spatiotemporal Kriging](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16575) | [Code](https:\u002F\u002Fgithub.com\u002FKaimaoge\u002FIGNNK) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKaimaoge\u002FIGNNK?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKaimaoge\u002FIGNNK?color=critical&style=social) | AAAI\u003Cbr>2021\n| Imputation | Activity \u003Cbr> PhysioNet \u003Cbr> Air Quality | SSGAN | [Generative Semi-supervised Learning for Multivariate Time Series Imputation](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17086) | [Code](https:\u002F\u002Fgithub.com\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation?color=critical&style=social) | AAAI\u003Cbr>2021\n| Imputation & \u003Cbr> Multivariat | PhysioNet \u003Cbr> Air Quality | CSDI | [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fcfe8504bda37b575c70ee1a8276f3486-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fermongroup\u002FCSDI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fermongroup\u002FCSDI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fermongroup\u002FCSDI?color=critical&style=social) | NeurIPS 2021\n| Imputation & \u003Cbr> Prediction | VevoMusic \u003Cbr> WikiTraffic \u003Cbr> Los-Loop \u003Cbr> SZ-Taxi | Radflow | [Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3442381.3449945) | [Code](https:\u002F\u002Fgithub.com\u002Falasdairtran\u002Fradflow) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falasdairtran\u002Fradflow?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falasdairtran\u002Fradflow?color=critical&style=social) | WWW 2021\n| Imputation | PhysioNet \u003Cbr> Air Quality \u003Cbr> Gas Sensor | STING | [STING: Self-attention based Time-series Imputation Networks using GAN](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679183) | None | ICDM 2021\n| Imputation | Zero \u003Cbr> MICE \u003Cbr> SoftImpute \u003Cbr> GMMC \u003Cbr> GAIN | SN | [Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=BylsKkHYvH) | [Future](https:\u002F\u002Fgithub.com\u002FJoonyoungYi\u002Fsparsity-normalization) | ICLR\u003Cbr>2020\n| Imputation | Beijing Air \u003Cbr> PhysioNet \u003Cbr> Porto Taxi \u003Cbr> London Weather | LGnet | [Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6056) | None | AAAI\u003Cbr>2020\n| Imputation | Sydney \u003Cbr> Melbourne \u003Cbr> Brisbane \u003Cbr> Perth, etc | SMV-NMF | [A spatial missing value imputation method for multi-view urban statistical data](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0182.pdf) | [Matlab](https:\u002F\u002Fgithub.com\u002FSMV-NMF\u002FSMV-NMF) | IJCAI\u003Cbr>2020\n| Imputation | PhysioNet \u003Cbr> Air Quality \u003Cbr> Wind | GANGRUI | [Adversarial Recurrent Time Series Imputation](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9158560\u002F) | None | TNNLS 2020\n| Imputation | Healthcare \u003Cbr> Climate | GRU-ODE-Bayes | [GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F455cb2657aaa59e32fad80cb0b65b9dc-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fedebrouwer\u002Fgru_ode_bayes) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fedebrouwer\u002Fgru_ode_bayes?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fedebrouwer\u002Fgru_ode_bayes?color=critical&style=social) | NeurIPS 2019\n| Imputation | Toy | LatenODE | [Latent Ordinary Differential Equations for Irregularly-Sampled Time Series](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F42a6845a557bef704ad8ac9cb4461d43-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002FYuliaRubanova\u002Flatent_ode) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYuliaRubanova\u002Flatent_ode?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYuliaRubanova\u002Flatent_ode?color=critical&style=social) | NeurIPS 2019\n| Imputation | Sines \u003Cbr> Stocks\u003Cbr> Energy \u003Cbr> Events | TimeGAN | [Time-series Generative Adversarial Networks](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fc9efe5f26cd17ba6216bbe2a7d26d490-Abstract.html) | [TF](https:\u002F\u002Fgithub.com\u002Fjsyoon0823\u002FTimeGAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjsyoon0823\u002FTimeGAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjsyoon0823\u002FTimeGAN?color=critical&style=social) | NeurIPS 2019\n| Imputation | MIMIC-III \u003Cbr> UWaveGesture | Inter-net | [Interpolation-Prediction Networks for Irregularly Sampled Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1efr3C9Ym) | [Keras](https:\u002F\u002Fgithub.com\u002Fmlds-lab\u002Finterp-net) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmlds-lab\u002Finterp-net?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmlds-lab\u002Finterp-net?color=critical&style=social) | ICLR\u003Cbr>2019\n| Imputation | PhysioNet \u003Cbr> KDD2018 | E2gan | [E2gan: End-to-end generative adversarial network for multivariate time series imputation](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0429.pdf) | [TF](https:\u002F\u002Fgithub.com\u002FLuoyonghong\u002FE2EGAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLuoyonghong\u002FE2EGAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLuoyonghong\u002FE2EGAN?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Imputation | EC \u003Cbr> RV | STI | [How Do Your Neighbors Disclose Your Information: Social-Aware Time Series Imputation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313714) | [Code](https:\u002F\u002Fgithub.com\u002Ftomstream\u002FSTI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftomstream\u002FSTI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftomstream\u002FSTI?color=critical&style=social) | WWW 2019\n\n\n# [Time Series Anomaly Detection](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums: 30+ | \u003Cimg width=90\u002F> | | | | \u003Cimg width=320\u002F> |\n| Anomaly Detection | Yahoo \u003Cbr> KPI \u003Cbr> WSD \u003Cbr> NAB | FCVAE | [Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3589334.3645710) | [Code](https:\u002F\u002Fgithub.com\u002FCSTCloudOps\u002FFCVAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCSTCloudOps\u002FFCVAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCSTCloudOps\u002FFCVAE?color=critical&style=social) | WWW 2024\n| Anomaly Detection | TODS \u003Cbr> ASD\u003Cbr> ECG \u003Cbr>PSM \u003Cbr> CompanyA | Dual-TF | [Breaking the Time-Frequency Granularity Discrepancy in Time-Series Anomaly Detection](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3589334.3645556) | [Code](https:\u002F\u002Fgithub.com\u002Fkaist-dmlab\u002FDualTF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkaist-dmlab\u002FDualTF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkaist-dmlab\u002FDualTF?color=critical&style=social) | WWW 2024\n| Anomaly Detection | SMD \u003Cbr> J-D1 \u003Cbr> J-D2 \u003Cbr>SMAP | LARA | [LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3589334.3645472) | None | WWW 2024\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> PSM \u003Cbr> SMD \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> Crediy \u003Cbr> Yahoo | | [When Model Meets New Normals: Test-Time Adaptation for Unsupervised Time-Series Anomaly Detection](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29210) | [Code](https:\u002F\u002Fgithub.com\u002FForestsKing\u002FD3R) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FForestsKing\u002FD3R?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FForestsKing\u002FD3R?color=critical&style=social) | AAAI\u003Cbr>2024\n| Anomaly Detection | SMD \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> SWaT \u003Cbr> PSM | MEMTO | [MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fb4c898eb1fb556b8d871fbe9ead92256-Abstract-Conference.html) | No | NIPS\u003Cbr>2023\n| Anomaly Detection | PSM \u003Cbr> SMD \u003Cbr> SWaT | D3R | [Drift doesn’t Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F22f5d8e689d2a011cd8ead552ed59052-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002FForestsKing\u002FD3R) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FForestsKing\u002FD3R?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FForestsKing\u002FD3R?color=critical&style=social) | NIPS\u003Cbr>2023\n| Anomaly Detection |SWaT \u003Cbr> WADI \u003Cbr> PSM \u003Cbr> MSL \u003Cbr> SMD \u003Cbr> trimSyn | Framework | [Nominality Score Conditioned Time Series Anomaly Detection by Point\u002FSequential Reconstruction](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F22f5d8e689d2a011cd8ead552ed59052-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fandrewlai61616\u002FNPSR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fandrewlai61616\u002FNPSR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fandrewlai61616\u002FNPSR?color=critical&style=social) | NIPS\u003Cbr>2023\n| Anomaly Detection | SMD \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> PSM \u003Cbr> DND| PUAD | [Prototype-oriented unsupervised anomaly detection for multivariate time series](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fli23d.html) | [Code](https:\u002F\u002Fgithub.com\u002FLiYuxin321\u002FPUAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiYuxin321\u002FPUAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiYuxin321\u002FPUAD?color=critical&style=social) | ICML\u003Cbr>2023\n| Anomaly Detection |UCR \u003Cbr>SMD | surrogate | [Unsupervised Model Selection for Time Series Anomaly Detection](https:\u002F\u002Fopenreview.net\u002Fforum?id=gOZ_pKANaPW) | [Author](https:\u002F\u002Fgithub.com\u002Fmononitogoswami) | ICLR\u003Cbr>2023\n| Anomaly Detection | MSL \u003Cbr> SMAP \u003Cbr> PSM \u003Cbr> SMD | DCdetector | [DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599295) | [Code](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FKDD2023-DCdetector) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDAMO-DI-ML\u002FKDD2023-DCdetector?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDAMO-DI-ML\u002FKDD2023-DCdetector?color=critical&style=social) | KDD\u003Cbr>2023\n| Anomaly Detection | MSL \u003Cbr> SWaT \u003Cbr> WADI | PoA | [Precursor-of-Anomaly Detection for Irregular Time Series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599469) | [Code](https:\u002F\u002Fgithub.com\u002Fsheoyon-jhin\u002FPAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsheoyon-jhin\u002FPAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsheoyon-jhin\u002FPAD?color=critical&style=social) | KDD\u003Cbr>2023\n| Anomaly Detection | MSL \u003Cbr> SWaT \u003Cbr> PSM \u003Cbr> SMAP \u003Cbr> SMD | DiffAD | [Imputation-based Time-Series Anomaly Detection with Conditional Weight-Incremental Diffusion Models](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599391) | [Code](https:\u002F\u002Fgithub.com\u002FChunjingXiao\u002FDiffAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChunjingXiao\u002FDiffAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FChunjingXiao\u002FDiffAD?color=critical&style=social) | KDD\u003Cbr>2023\n| Anomaly Detection |SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT | DAEMON | [Adversarial Autoencoder for Unsupervised Time Series Anomaly Detection and Interpretation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570371) | [Code](https:\u002F\u002Fgithub.com\u002FSherlock-C\u002FDAEMON) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSherlock-C\u002FDAEMON?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSherlock-C\u002FDAEMON?color=critical&style=social) | AAAI\u003Cbr>2023\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> PSM \u003Cbr> MSL \u003Cbr> SMD | MTGFlow | [Detecting Multivariate Time Series Anomalies with Zero Known Label](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25623) | [Code](https:\u002F\u002Fgithub.com\u002Fzqhang\u002FMTGFLOW) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzqhang\u002FMTGFLOW?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzqhang\u002FMTGFLOW?color=critical&style=social) | AAAI\u003Cbr>2023\n| Anomaly Detection | SWaT \u003Cbr> WADI SMAP \u003Cbr> MSL | DuoGAT | [DuoGAT: Dual Time-oriented Graph Attention Networks for Accurate, Efficient and Explainable Anomaly Detection on Time-series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614857) | [Code](https:\u002F\u002Fgithub.com\u002FByeongtaePark\u002FDuoGAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FByeongtaePark\u002FDuoGAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FByeongtaePark\u002FDuoGAT?color=critical&style=social) | CIKM\u003Cbr>2023\n| Anomaly Detection | SWaT \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> PSM \u003Cbr> SMD | MadSGM | [MadSGM: Multivariate Anomaly Detection with Score-based Generative Models](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614857) | None | CIKM\u003Cbr>2023\n| Anomaly Detection |SMD \u003Cbr> Boiler | ContexTDA | [Context-aware Domain Adaptation for Time Series Anomaly Detection](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch76) | None| SDM 2023\n| Anomaly Detection | AIOps \u003Cbr> UCR | COCA | [Deep Contrastive One-Class Time Series Anomaly Detection](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch78) | [Merlion,Tsaug ](https:\u002F\u002Fgithub.com\u002Fruiking04\u002FCOCA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fruiking04\u002FCOCA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fruiking04\u002FCOCA?color=critical&style=social) | SDM 2023\n| Anomaly Detection | DND \u003Cbr> SMD \u003Cbr> MSL \u003Cbr> SMAP | DVGCRN | [Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fchen22x.html) | [Future](https:\u002F\u002Fgithub.com\u002FBoChenGroup) | ICML\u003Cbr>2022\n| Anomaly Detection | YelpChi \u003Cbr> Amazon \u003Cbr> T-Finance \u003Cbr> T-Social | BWGNN | [Rethinking Graph Neural Networks for Anomaly Detection](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Ftang22b.html) | [Code](https:\u002F\u002Fgithub.com\u002FsquareRoot3\u002FRethinking-Anomaly-Detection) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FsquareRoot3\u002FRethinking-Anomaly-Detection?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FsquareRoot3\u002FRethinking-Anomaly-Detection?color=critical&style=social) | ICML\u003Cbr>2022\n| Anomaly Detection | SMD \u003Cbr> PSM \u003Cbr> MSL&SMAP \u003Cbr> SWaT \u003Cbr> NeurIPS-TS | Anomaly Transformer | [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https:\u002F\u002Fopenreview.net\u002Fforum?id=LzQQ89U1qm_) | [Code](https:\u002F\u002Fgithub.com\u002Fspencerbraun\u002Fanomaly_transformer_Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspencerbraun\u002Fanomaly_transformer_Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fspencerbraun\u002Fanomaly_transformer_Code?color=critical&style=social) | ICLR\u003Cbr>2022\n| Density Estimation & Anomaly Detection | PMU-B \u003Cbr> PMU-C \u003Cbr> SWaT \u003Cbr> METR-LA | GANF | [Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=45L_dgP48Vd) | [Code](https:\u002F\u002Fgithub.com\u002FEnyanDai\u002FGANF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEnyanDai\u002FGANF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEnyanDai\u002FGANF?color=critical&style=social) | ICLR\u003Cbr>2022\n| Anomaly Detection | | | [Anomaly Detection for Tabular Data with Internal Contrastive Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=_hszZbt46bT) | None | ICLR\u003Cbr>2022\n| Anomaly Detection | Machine-Temp \u003Cbr> NYCTaxi \u003Cbr> Twitter \u003Cbr> SWaT | algorithmic | [Local Evaluation of Time Series Anomaly Detection Algorithms](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539339) | [Python](https:\u002F\u002Fgithub.com\u002Fahstat\u002Faffiliation-metrics-py) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fahstat\u002Faffiliation-metrics-py?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fahstat\u002Faffiliation-metrics-py?color=critical&style=social) | KDD\u003Cbr>2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> HAI | FuSAGNet | [Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539117) | [Code](https:\u002F\u002Fgithub.com\u002Fsihohan\u002FFuSAGNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsihohan\u002FFuSAGNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsihohan\u002FFuSAGNet?color=critical&style=social) | KDD\u003Cbr>2022\n| Anomaly Detection | Slef-defined | RCAD | [RCAD: Real-time Collaborative Anomaly Detection System for Mobile Broadband Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539097) | [Code](https:\u002F\u002Fgithub.com\u002Fazza8903\u002FHTM-MODEL_EXCHANGE\u002F) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fazza8903\u002FHTM-MODEL_EXCHANGE\u002F?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fazza8903\u002FHTM-MODEL_EXCHANGE\u002F?color=critical&style=social) | KDD\u003Cbr>2022\n| Anomaly Detection | | AnomalyKiTS | [AnomalyKiTS-Anomaly Detection Toolkit for Time Series](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_dm318) | None | AAAI\u003Cbr>2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> SMD | PA | [Towards a Rigorous Evaluation of Time-Series Anomaly Detection](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai2239) | None | AAAI\u003Cbr>2022\n| Anomaly Detection | YAHOO \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> PSM | NCAD | [Neural Contextual Anomaly Detection for Time Series](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F332) | [Future](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluon-ts\u002Ftree\u002Fdev\u002Fsrc\u002Fgluonts\u002Fnursery) | IJCAI\u003Cbr>2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> PSM | GRELEN | [GRELEN: Multivariate Time Series Anomaly Detection from the Perspective of Graph Relational Learning](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F394) | None| IJCAI\u003Cbr>2022\n| Anomaly Detection | MSL \u003Cbr> SMAP \u003Cbr> MNIST \u003Cbr> ,etc | CADET | [CADET: Calibrated Anomaly Detection for Mitigating Hardness Bias](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F278) | [Future](https:\u002F\u002Fgithub.com\u002Fd-ailin\u002FCADET)| IJCAI\u003Cbr>2022\n| Anomaly Detection | ECG \u003Cbr> HAR \u003Cbr> MNIST | | [Understanding and Mitigating Data Contamination in Deep Anomaly Detection: A Kernel-based Approach](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F322) | None | IJCAI\u003Cbr>2022\n| Anomaly Detection | Business| SLA-VAE | [A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3511984) | None| WWW 2022\n| Anomaly Detection | KDDCUP99 \u003Cbr> NSL \u003Cbr> UNSW, etc | MemStream | [MemStream: Memory-Based Streaming Anomaly Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3511984) | [Code](https:\u002F\u002Fgithub.com\u002FStream-AD\u002FMemStream)| \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FStream-AD\u002FMemStream?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FStream-AD\u002FMemStream?color=critical&style=social) WWW 2022\n| Anomaly Detection | GD \u003Cbr> HSS \u003Cbr> ECG \u003Cbr> NAB \u003Cbr> Yahoo S5 \u003Cbr> 2D \u003Cbr> SYN | RDAE | [Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835554) | [Author](https:\u002F\u002Fgithub.com\u002Ftungk) | ICDE 2022\n| Anomaly Detection | GD \u003Cbr> HSS \u003Cbr> ECG \u003Cbr> TD \u003Cbr> Yahoo S5 | BiVQRAEs | [Anomaly Detection in Time Series with Robust Variational Quasi-Recurrent Autoencoders](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835268) | [Code](https:\u002F\u002Fgithub.com\u002Ftungk\u002FBi-VQRAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftungk\u002FBi-VQRAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftungk\u002FBi-VQRAE?color=critical&style=social) | ICDE 2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> BATADAL | MAD-SGCN | [MAD-SGCN: Multivariate Anomaly Detection with Self-learning Graph Convolutional Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9835470) | None | ICDE 2022\n| Anomaly Detection | NAB \u003Cbr> UCR \u003Cbr> MBA \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> MSDS | TranAD | [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https:\u002F\u002Fdoi.org\u002F10.14778\u002F3514061.3514067) | [Code](https:\u002F\u002Fgithub.com\u002Fimperial-qore\u002FTranAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fimperial-qore\u002FTranAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fimperial-qore\u002FTranAD?color=critical&style=social) | VLDB 2022\n| Anomaly Detection | KPI \u003Cbr> Yahoo \u003Cbr> SMAP \u003Cbr> MSL | TFAD | [TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557470) | [Code](https:\u002F\u002Fgithub.com\u002Fdamo-di-ml\u002Fcikm22-tfad) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdamo-di-ml\u002Fcikm22-tfad?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdamo-di-ml\u002Fcikm22-tfad?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | SMAP \u003Cbr> MSL \u003Cbr> SMD \u003Cbr> KARI \u003Cbr> Synthetic | Attack | [Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557073) | [Code](https:\u002F\u002Fgithub.com\u002Fshahroztariq\u002FAdversarial-Attacks-on-Timeseries) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshahroztariq\u002FAdversarial-Attacks-on-Timeseries?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshahroztariq\u002FAdversarial-Attacks-on-Timeseries?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | Cora \u003Cbr> Citeseer \u003Cbr> PubMed \u003Cbr> Flickr \u003Cbr> ogbn-arxiv | LHML | [Learning Hypersphere for Few-shot Anomaly Detection on Attributed Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557377) | [Code](https:\u002F\u002Fgithub.com\u002FEureka-GQY\u002FLHML) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEureka-GQY\u002FLHML?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEureka-GQY\u002FLHML?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | RT \u003Cbr> NetSpd | RobustDTW | [Robust Time Series Dissimilarity Measure for Outlier Detection and Periodicity Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557686) | None | CIKM\u003Cbr>2022\n| Anomaly Detection | CIFAR-1 \u003Cbr> CIFAR-10 \u003Cbr> Caltech 10 | SLA2 | [Self-supervision Meets Adversarial Perturbation: A Novel Framework for Anomaly Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557697) | [Code](https:\u002F\u002Fgithub.com\u002Fwyzjack\u002FSLA2P) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwyzjack\u002FSLA2P?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwyzjack\u002FSLA2P?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | SMD | FDRC | [Online false discovery rate control for anomaly detection in time series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467075) | Nçone | NeurIPS 2021\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> ASD | InterFusion | [Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding](https:\u002F\u002Fpapers.NeurIPS.cc\u002Fpaper\u002F2021\u002Fhash\u002Fdef130d0b67eb38b7a8f4e7121ed432c-Abstract.html) | [TF](https:\u002F\u002Fgithub.com\u002Fzhhlee\u002FInterFusion) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhhlee\u002FInterFusion?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhhlee\u002FInterFusion?color=critical&style=social) | KDD\u003Cbr>2021\n| Anomaly Detection | SMD \u003Cbr> SWaT \u003Cbr> PSM \u003Cbr> BKPI | RANSynCoders | [Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467174) | [TF](https:\u002F\u002Fgithub.com\u002FeBay\u002FRANSynCoders) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FeBay\u002FRANSynCoders?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FeBay\u002FRANSynCoders?color=critical&style=social) | KDD\u003Cbr>2021\n| Anomaly Detection | PUMP \u003Cbr> WADI \u003Cbr> SWaT | NSIBF | [Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467137) | [TF](https:\u002F\u002Fgithub.com\u002FNSIBF\u002FNSIBF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNSIBF\u002FNSIBF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNSIBF\u002FNSIBF?color=critical&style=social) | KDD\u003Cbr>2021\n| Anomaly Detection | SWaT \u003Cbr> WADI | GDN | [Graph Neural Network-Based Anomaly Detection in Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16523) | [Code](https:\u002F\u002Fgithub.com\u002Fd-ailin\u002FGDN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fd-ailin\u002FGDN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fd-ailin\u002FGDN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Anomaly Detection | SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT | DAEMON | [DAEMON: Unsupervised Anomaly Detection and Interpretation for Multivariate Time Series](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458835) | [Future](https:\u002F\u002Fgithub.com\u002FAzerrroth\u002FDAEMON) | ICDE 2021\n| Anomaly Detection | KPI \u003Cbr> Yahoo | FluxEV | [FluxEV: A Fast and Effective Unsupervised Framework for Time-Series Anomaly Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441823) | [Py](https:\u002F\u002Fgithub.com\u002Fjlidw\u002FFluxEV) | WSDM 2021\n| Anomaly Detection | [DataLink](https:\u002F\u002Fcompete.hexagon-ml.com\u002Fpractice\u002Fcompetition\u002F39\u002F)| Benchmark | [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9537291) | None | TKDE 2021\n| Earthquakes Detection | NIED | CrowdQuake | [A Networked System of Low-Cost Sensors for Earthquake Detection via Deep Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403378) | [TF](https:\u002F\u002Fgithub.com\u002Fxhuang2016\u002FSeismic-Detection) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxhuang2016\u002FSeismic-Detection?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxhuang2016\u002FSeismic-Detection?color=critical&style=social) | KDD\u003Cbr>2020\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> Orange | USAD | [USAD: UnSupervised Anomaly Detection on Multivariate Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403392) | [Code](https:\u002F\u002Fgithub.com\u002Fmanigalati\u002Fusad) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmanigalati\u002Fusad?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmanigalati\u002Fusad?color=critical&style=social) | KDD\u003Cbr>2020\n| Anomaly Detection | NYC | CHAT | [Cross-interaction hierarchical attention networks for urban anomaly prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.5555\u002F3491440.3492041) | None | IJCAI\u003Cbr>2020\n| Anomaly Detection | NYC-Bike \u003Cbr> NYC-Taxi \u003Cbr> Weather \u003Cbr> NYC-POI \u003Cbr> NYC-Anomaly | DST-MFN | [Deep Spatio-Temporal Multiple Domain Fusion Network for Urban Anomalies Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411920) | None | CIKM\u003Cbr>2020\n| Anomaly Detection | SMAP \u003Cbr> MSL \u003Cbr> TSA | MTAD-GAT | [Multivariate Time-Series Anomaly Detection via Graph Attention Network](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338317) | [TF](https:\u002F\u002Fgithub.com\u002Fmangushev\u002Fmtad-gat) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmangushev\u002Fmtad-gat?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmangushev\u002Fmtad-gat?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002FML4ITS\u002Fmtad-gat-Code) | ICDM 2020\n| Anomaly Detection | SMAP \u003Cbr> MSL \u003Cbr> SMD | OmniAnomaly | [Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330672) | [TF](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002FOmniAnomaly) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNetManAIOps\u002FOmniAnomaly?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNetManAIOps\u002FOmniAnomaly?color=critical&style=social) | KDD\u003Cbr>2019\n| Anomaly Detection | GeoLife \u003Cbr> TST | IRL-ADU | [Sequential Anomaly Detection using Inverse Reinforcement Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330932) | None | KDD\u003Cbr>2019\n| Anomaly Detection | donors \u003Cbr> census \u003Cbr> fraud \u003Cbr> celeba ,etc | DevNet | [Deep Anomaly Detection with Deviation Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330871) | [Keras](https:\u002F\u002Fgithub.com\u002FGuansongPang\u002Fdeviation-network) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGuansongPang\u002Fdeviation-network?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGuansongPang\u002Fdeviation-network?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002FChoubo\u002Fdeviation-network-image) | KDD\u003Cbr>2019\n| Anomaly Detection | KPI \u003Cbr> Yahoo \u003Cbr> Microsoft | SR-CNN | [Time-Series Anomaly Detection Service at Microsoft](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330680) | None | KDD\u003Cbr>2019\n| Anomaly Detection | power plant | MSCRED | [A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3942) | [TF](https:\u002F\u002Fgithub.com\u002F7fantasysz\u002FMSCRED) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002F7fantasysz\u002FMSCRED?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002F7fantasysz\u002FMSCRED?color=critical&style=social) | AAAI\u003Cbr>2019\n| Anomaly Detection | ECG \u003Cbr> Motion | BeatGAN | [BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0616.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Fhi-bingo\u002FBeatGAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhi-bingo\u002FBeatGAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhi-bingo\u002FBeatGAN?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Anomaly Detection | NAB \u003Cbr> ECG | OED | [Outlier Detection for Time Series with Recurrent Autoencoder Ensembles](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0378.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Ftungk\u002FOED) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftungk\u002FOED?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftungk\u002FOED?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Anomaly Detection | KPIs | Buzz | [Unsupervised Anomaly Detection for Intricate KPIs via Adversarial Training of VAE](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8737430) | [TF](https:\u002F\u002Fgithub.com\u002Fyantijin\u002FBuzz) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyantijin\u002FBuzz?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyantijin\u002FBuzz?color=critical&style=social) | INFOCOM 2019\n| Anomaly Detection | KDDCUP \u003Cbr> Thyroid \u003Cbr> Arrhythmia \u003Cbr> KDDCUP-Rev | DAGMM | [Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection](https:\u002F\u002Fopenreview.net\u002Fforum?id=BJJLHbb0-) | [Code](https:\u002F\u002Fgithub.com\u002Fdanieltan07\u002Fdagmm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdanieltan07\u002Fdagmm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdanieltan07\u002Fdagmm?color=critical&style=social) | ICLR\u003Cbr>2018\n| Anomaly Detection | SMAP \u003Cbr> MSL | telemanom | [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3219819.3219845) | [TF](https:\u002F\u002Fgithub.com\u002Fkhundman\u002Ftelemanom) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkhundman\u002Ftelemanom?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkhundman\u002Ftelemanom?color=critical&style=social) | KDD\u003Cbr>2018\n| Anomaly Detection | AD \u003Cbr> AID362 \u003Cbr> aPascal \u003Cbr> BM , etc| CINFO | [Sparse Modeling-Based Sequential Ensemble Learning for Effective Outlier Detection in High-Dimensional Numeric Data](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11692) | [Matlab](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F0B_GL5U7rPj1xNzNwTHpHSzZkQXM\u002Fview?resourcekey=0-HneFEhC8NUIWDfhmfaOyBQ) | AAAI\u003Cbr>2018\n| Anomaly Detection | KPIs | Donut | [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3178876.3185996) | [TF](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002Fdonut) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNetManAIOps\u002Fdonut?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNetManAIOps\u002Fdonut?color=critical&style=social) | WWW 2018\n| Anomaly Detection | MAWI | DSPOT | [Anomaly Detection in Streams with Extreme Value Theory](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3097983.3098144) | [Python](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002Fdonut) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNetManAIOps\u002Fdonut?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNetManAIOps\u002Fdonut?color=critical&style=social) | KDD\u003Cbr>2017\n| Anomaly Detection | Power \u003Cbr> Space \u003Cbr> Engine \u003Cbr> ECG | EncDec-AD | [ LSTM-based encoder-decoder for multi-sensor anomaly detection](https:\u002F\u002Fwww.semanticscholar.org\u002Fpaper\u002FLSTM-based-Encoder-Decoder-for-Multi-sensor-Anomaly-Malhotra-Ramakrishnan\u002Fe9672150c4f39ab64876e798a94212a93d1770fe) | [Code](https:\u002F\u002Fgithub.com\u002Fjaeeun49\u002FAnomaly-Detection\u002Fblob\u002Fmain\u002Fcode_practices\u002FLSTM-based%20Encoder-Decoder%20for%20Multi-sensor%20Anomaly%20Detection.ipynb) | ICML\u003Cbr>2016\n| Anomaly Detection | MORE | MORE | [https:\u002F\u002Fgithub.com\u002FZIYU-DEEP\u002FIJCAI-Paper-List-of-Anomaly-Detection](https:\u002F\u002Fgithub.com\u002FZIYU-DEEP\u002FIJCAI-Paper-List-of-Anomaly-Detection) | MORE | IJCAI\n| Anomaly Detection | MORE | MORE | [DeepTimeSeriesModel](https:\u002F\u002Fgithub.com\u002Fdrzhang3\u002FDeepTimeSeriesModel) | MORE | MORE\n| Anomaly Detection | MORE | MORE | [GuansongPang](https:\u002F\u002Fgithub.com\u002FGuansongPang\u002FSOTA-Deep-Anomaly-Detection) | MORE | MORE\n\n\n\n\n# [Demand Prediction](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-:| - |\n| Paper Nums: 30+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| Travel \u003Cbr> Demand | CDP \u003Cbr> SLD | STTD | [Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614918) | [Code](https:\u002F\u002Fgithub.com\u002FSTTDAnonymous\u002FSTTD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSTTDAnonymous\u002FSTTD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSTTDAnonymous\u002FSTTD?color=critical&style=social) | CIKM\u003Cbr>2023\n| Travel \u003Cbr> Demand | NYC Bike \u003Cbr> NYC Taxi | AGND | [Adaptive Graph Neural Diffusion for Traffic Demand Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615153) | None | CIKM\u003Cbr>2023\n| Traffic Demand | BJSubway \u003Cbr> NYCTaxi | CMOD | [Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539273) | [Code](https:\u002F\u002Fgithub.com\u002Fliangzhehan\u002FCMOD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliangzhehan\u002FCMOD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliangzhehan\u002FCMOD?color=critical&style=social) | KDD\u003Cbr>2022\n| Job Demand | IT \u003Cbr> FIN \u003Cbr> CONS | DH-GEM | [Talent Demand-Supply Joint Prediction with Dynamic Heterogeneous Graph Enhanced Meta-Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539139) | [Code](https:\u002F\u002Fgithub.com\u002Fgzn00417\u002FDH-GEM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgzn00417\u002FDH-GEM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgzn00417\u002FDH-GEM?color=critical&style=social) | KDD\u003Cbr>2022\n| Supply & \u003Cbr> Demand | JONAS-NYC \u003Cbr> JONAS-DC \u003Cbr> COVID-CHI \u003Cbr> COVID-US | EAST-Net | [Event-Aware Multimodal Mobility Nowcasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai10914) | [Code](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FEAST-Net) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FEAST-Net?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FEAST-Net?color=critical&style=social) | AAAI\u003Cbr>2022\n| Health Demand | Family Van | framework | [Using Public Data to Predict Demand for Mobile Health Clinics](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_emer91) | None | AAAI\u003Cbr>2022\n| Traffic Demand | BJMetro \u003Cbr> NYCTaxi | HMOD | [Dynamic Graph Learning Based on Hierarchical Memory for Origin-Destination Demand Prediction](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F331) | [Code](https:\u002F\u002Fgithub.com\u002FRising0321\u002FHMOD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRising0321\u002FHMOD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRising0321\u002FHMOD?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Traffic Demand | Chicago \u003Cbr> LosAngeles | STGNN-DJD | [A Data-Driven Spatial-Temporal Graph Neural Network for Docked Bike Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9835338) | [Code](https:\u002F\u002Fgithub.com\u002FGuanyaoLI\u002FSTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGuanyaoLI\u002FSTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGuanyaoLI\u002FSTGNN?color=critical&style=social) | ICDE 2022\n| OD Demand | Shanghai \u003Cbr> Changsha \u003Cbr> Beijing | CausalOD | [Causal Learning Empowered OD Prediction for Urban Planning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557255) | [Code](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FSIRI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FSIRI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FSIRI?color=critical&style=social) | CIKM\u003Cbr>2022\n| OD Demand | NYC Taxi \u003Cbr> Haikou \u003Cbr> SZMetro | HSTN | [Origin-Destination Traffic Prediction based on Hybrid Spatio-Temporal Network](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027683) | [TF](https:\u002F\u002Fgithub.com\u002Fchentingyang\u002FHSTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchentingyang\u002FHSTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchentingyang\u002FHSTN?color=critical&style=social) | ICDM 2022\n| Traffic Demand | NYC Bike \u003Cbr> NYC Taxi | CCRNN | [Coupled Layer-wise Graph Convolution for Transportation Demand Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16591) | [Code](https:\u002F\u002Fgithub.com\u002FEssaim\u002FCGCDemandPrediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEssaim\u002FCGCDemandPrediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEssaim\u002FCGCDemandPrediction?color=critical&style=social) | AAAI\u003Cbr>2021\n| Traffic Demand | BaiduBJ \u003Cbr> BaiduSH | Ada-MSTNet | [Community-Aware Multi-Task Transportation Demand Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16107) | None | AAAI\u003Cbr>2021\n| Job Demand | Online | TDAN | [Talent Demand Forecasting with Attentive Neural Sequential Model](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467131) | None | KDD\u003Cbr>2021\n| Ambulance Demand | Tokyo | EMS-Pred | [Forecasting Ambulance Demand with Profiled Human Mobility via Heterogeneous Multi-Graph Neural Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458623) | [Code](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FEMS-Pred-ICDE-21) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FEMS-Pred-ICDE-21?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FEMS-Pred-ICDE-21?color=critical&style=social) | ICDE 2021\n| Passenger Demand | TaxiNYC | SOUP | [SOUP: A Fleet Management System for Passenger Demand Prediction and Competitive Taxi Supply](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458616) | None | ICDE 2021\n| Passenger Demand | DiDiBJ \u003Cbr> DiDiSH| Gallat | [Gallat: A Spatiotemporal Graph Attention Network for Passenger Demand Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458919) | None | ICDE 2021\n| Traffic Demand \u003Cbr> Traffic Flow | Chengdu \u003Cbr> Xian| DeepTP | [An Effective Joint Prediction Model for Travel Demands and Traffic Flows](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458698) | None | ICDE 2021\n| Traffic Demand | DiDiCD \u003Cbr> NYCTaxi | DAGNN | [Dynamic Auto-structuring Graph Neural Network-A Joint Learning Framework for Origin-Destination Demand Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9657493) | None | TKDE 2021\n| Traffic Demand | TaxiNYC \u003Cbr> CitiBikeNYC | MultiAttConvLSTM | [Multi-level attention networks for multi-step citywide passenger demands prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8873676\u002F) | None | TKDE 2021\n| Market Demand | Juhuasuan \u003Cbr> Tiantiantemai | RMLDP | [Relation-aware Meta-learning for E-commerce Market Segment Demand Prediction with Limited Records](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441750) | None | WSDM 2021\n| Metro Demand | MetroBJ2016 \u003Cbr> MetroBJ2018 | CAS | [Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.trc.2020.102928) | None | Transportation Research Part C 2021\n| Metro Demand | MetroBJ2016 \u003Cbr> MetroBJ2018 | ST-ED | [Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.trc.2020.102858) | None | Transportation Research Part C 2021\n| Traffic Demand | Seattlebike | FairST | [Fairness-Aware Demand Prediction for New Mobility](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5458) | None | AAAI\u003Cbr>2020\n| Drug Demand | Wikipedia | None | [Predicting Drug Demand with Wikipedia Views: Evidence from Darknet Markets](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380022) | None | WWW 2020\n| Traffic Demand | DiDiBJ \u003Cbr> DiDiSH | MPGCN | [Predicting Origin-Destination Flow via Multi-Perspective Graph Convolutional Network](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9101359) | [Code](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FMPGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FMPGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FMPGCN?color=critical&style=social) | ICDE 2020\n| Traffic Demand | NYC \u003Cbr> DiDiCD | MPGCN | [Stochastic Origin-Destination Matrix Forecasting Using Dual-Stage Graph Convolutional, Recurrent Neural Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9101647\u002F) | [TF](https:\u002F\u002Fgithub.com\u002Fhujilin1229\u002Fod-pred) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhujilin1229\u002Fod-pred?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhujilin1229\u002Fod-pred?color=critical&style=social) | ICDE 2020\n| Traffic Demand | Bengaluru \u003Cbr> NYC | GraphLSTM | [Grids Versus Graphs: Partitioning Space for Improved Taxi Demand-Supply Forecasts](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9099450\u002F) | [Code](https:\u002F\u002Fgithub.com\u002FNDavisK\u002FGrids-versus-Graphs) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNDavisK\u002FGrids-versus-Graphs?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNDavisK\u002FGrids-versus-Graphs?color=critical&style=social) | TITS 2020\n| Traffic Demand | NYCbike \u003Cbr> NYCtaxi | CoST-Net | [Co-Prediction of Multiple Transportation Demands Based on Deep Spatio-Temporal Neural Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330887) | None | KDD\u003Cbr>2019\n| Traffic Demand | UCAR \u003Cbr> DiDiCD | GEML | [Origin-Destination Matrix Prediction via Graph Convolution: a New Perspective of Passenger Demand Modeling](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330877) | [Keras](https:\u002F\u002Fgithub.com\u002FZekun-Cai\u002FGEML-Origin-Destination-Matrix-Prediction-via-Graph-Convolution) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZekun-Cai\u002FGEML-Origin-Destination-Matrix-Prediction-via-Graph-Convolution?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZekun-Cai\u002FGEML-Origin-Destination-Matrix-Prediction-via-Graph-Convolution?color=critical&style=social) | KDD\u003Cbr>2019\n| Traffic Demand | NYCbike \u003Cbr> Meso West | CE-LSTM | [Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3890) | None | AAAI\u003Cbr>2019\n| Traffic Demand | Beijing \u003Cbr> Shanghai | STMGCN | [Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4247) | [Code](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FST-MGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) | AAAI\u003Cbr>2019\n| Traffic Demand | NYC-TOD | CSTN | [Contextualized Spatial–Temporal Network for Taxi Origin-Destination Demand Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8720246\u002F) | [Keras](https:\u002F\u002Fgithub.com\u002Fliulingbo918\u002FCSTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliulingbo918\u002FCSTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliulingbo918\u002FCSTN?color=critical&style=social) | TITS 2019\n| Traffic Demand | NYCtaxi | MultiConvLSTM | [Deep Multi-Scale Convolutional LSTM Network for Travel Demand and Origin-Destination Predictions](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8758916\u002F) | None | TITS 2019\n| Traffic Demand | PEMS | t-SNE | [Estimating multi-year origin-destination demand using high-granular multi-source traffic data](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.trc.2018.09.002) | None | Transportation Research Part C 2018\n\n\n\n\n\u003C!-- | Traffic Demand | Electricity \u003Cbr> Traffic \u003Cbr> NYCTaxi \u003Cbr> Uber | framework | [Multi-Horizon Time Series Forecasting with Temporal Attention Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330662) | [Code](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FST-MGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) | KDD\u003Cbr>2019 \n-->\n\n# [Time Series Generation](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums: 6 | \u003Cimg width=90\u002F> | | | | \u003Cimg width=320\u002F> |\n| TS Generation | Stock \u003Cbr> Energy \u003Cbr> MuJoCo | ImagenTime | [Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=2NfBBpbN9x) | [Code](https:\u002F\u002Fgithub.com\u002Fazencot-group\u002FImagenTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fazencot-group\u002FImagenTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fazencot-group\u002FImagenTime?color=critical&style=social) | NIPS\u003Cbr>2024\n| TS Generation | AR1 \u003Cbr> Stock \u003Cbr> Energy \u003Cbr> Temperature \u003Cbr> ECG | FIDE | [FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series Generation](https:\u002F\u002Fopenreview.net\u002Fforum?id=5HQhYiGnYb) | [Code](https:\u002F\u002Fgithub.com\u002Fgalib19\u002FFIDE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgalib19\u002FFIDE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgalib19\u002FFIDE?color=critical&style=social) | NIPS\u003Cbr>2024\n| TS Generation | Electricity \u003Cbr> Traffic \u003Cbr> Exchange \u003Cbr> M4 \u003Cbr> UberTLC \u003Cbr> Solar \u003Cbr> KDDCup \u003Cbr> Wikipedia | ANT | [ANT: Adaptive Noise Schedule for Time Series Diffusion Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=1ojAkTylz4) | [glounts](https:\u002F\u002Fgithub.com\u002Fseunghan96\u002FANT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseunghan96\u002FANT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fseunghan96\u002FANT?color=critical&style=social) | NIPS\u003Cbr>2024\n| TS Generation | Sines \u003Cbr> Stocks \u003Cbr> ETTh \u003Cbr> MuJoCo \u003Cbr> Energy \u003Cbr> Solar \u003Cbr> fMRI | SDformer | [SDformer: Similarity-driven Discrete Transformer For Time Series Generation](https:\u002F\u002Fopenreview.net\u002Fforum?id=ZKbplMrDzI) | [Code](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002FSDformer-main\u002FREADME.md) | NIPS\u003Cbr>2024\n| TS Generation | Sines \u003Cbr> Stocks \u003Cbr> ETTh \u003Cbr> MuJoCo \u003Cbr> Energy \u003Cbr> Solar \u003Cbr> fMRI | Diffusion-TS | [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https:\u002F\u002Fopenreview.net\u002Fforum?id=4h1apFjO99) | [Code](https:\u002F\u002Fgithub.com\u002FY-debug-sys\u002FDiffusion-TS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FY-debug-sys\u002FDiffusion-TS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FY-debug-sys\u002FDiffusion-TS?color=critical&style=social) | ICLR\u003Cbr>2024\n| TS Generation | FRED-MD \u003Cbr> NN5 Daily \u003Cbr> Temp Rain \u003Cbr> Solar Weekly | LS4 | [Deep Latent State Space Models for Time-Series Generation](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fzhou23i.html) | [Code](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) | ICML\u003Cbr>2023\n| TS Generation | He ́non maps \u003Cbr> Lorenz \u003Cbr> fMRI \u003Cbr> EEG| CR-VAE | [Causal Recurrent Variational Autoencoder for Medical Time Series Generation](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26031) | [Code](https:\u002F\u002Fgithub.com\u002Fhongmingli1995\u002FCR-VAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) | AAAI\u003Cbr>2023\n| TS Generation | ETTh1 \u003Cbr> ETTh2 \u003Cbr> US Births \u003Cbr> ILI| AEC-GAN | [AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-Series Generation](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26208) | [Code](https:\u002F\u002Fgithub.com\u002Fhongmingli1995\u002FCR-VAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) | AAAI\u003Cbr>2023\n| TS Generation | UCR | TimeVQVAE | [Vector Quantized Time Series Generation with a Bidirectional Prior Model](https:\u002F\u002Fproceedings.mlr.press\u002Fv206\u002Flee23d.html) | [Code](https:\u002F\u002Fgithub.com\u002FML4ITS\u002FTimeVQVAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FML4ITS\u002FTimeVQVAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FML4ITS\u002FTimeVQVAE?color=critical&style=social) | AISTATS 2023 \n| TS Generation | USHCN \u003Cbr> KDD-CUP \u003Cbr> MIMIC-III| DGM | [Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16145) | [Code](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) | AAAI\u003Cbr>2021\n\n\n\n# [Travel Time Estimation](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums:20+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| Package Delivery \u003Cbr> TTE | Cainiao | GMDNet | [GMDNet: A Graph-Based Mixture Density Network for Estimating Packages’ Multimodal Travel Time Distribution](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25578) | [Code](https:\u002F\u002Fgithub.com\u002Fmaoxiaowei97\u002FGMDNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmaoxiaowei97\u002FGMDNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmaoxiaowei97\u002FGMDNet?color=critical&style=social) | AAAI\u003Cbr>2023\n| Delivery \u003Cbr> Time Estimation | Weihai \u003Cbr> Hangzhou | IGT | [Inductive Graph Transformer for Delivery Time Estimation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570409) | [Code](https:\u002F\u002Fgithub.com\u002Fenoche\u002FIGT-WSDM23) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fenoche\u002FIGT-WSDM23?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fenoche\u002FIGT-WSDM23?color=critical&style=social) | WSDM 2023\n| Delivery \u003Cbr> Time Estimation | JD and Amazon | STTD | [Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615215) | [Code](https:\u002F\u002Fgithub.com\u002FJD-HST-GT\u002FHST-GT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJD-HST-GT\u002FHST-GT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJD-HST-GT\u002FHST-GT?color=critical&style=social) | CIKM\u003Cbr>2023\n| TTE | Jinan City \u003Cbr> Nanjing City | GBTTE | [GBTTE: Graph Attention Network Based Bus Travel Time Estimation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614730) | None | CIKM\u003Cbr>2023\n| TTE | Beijing \u003Cbr> Guangzhou | HierETA | [Interpreting Trajectories from Multiple Views: A Hierarchical Self-Attention Network for Estimating the Time of Arrival](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539051) | [Code](https:\u002F\u002Fgithub.com\u002FYuejiaoGong\u002FHierETA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYuejiaoGong\u002FHierETA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYuejiaoGong\u002FHierETA?color=critical&style=social) | KDD\u003Cbr>2022\n| TTE | Beijing \u003Cbr> Porto | MetaER-TTE | [MetaER-TTE: An Adaptive Meta-learning Model for En Route Travel Time Estimation](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F281) | None | IJCAI\u003Cbr>2022\n| TTE | Beijing \u003Cbr> Shanghai \u003Cbr> Tianjin | DuETA | [DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557091) | None | CIKM\u003Cbr>2022\n| TTE | Baidu:\u003Cbr> Taiyuan \u003Cbr> Huizhou \u003Cbr> Hefei| SSML | [SSML: Self-Supervised Meta-Learner for En Route Travel Time Estimation at Baidu Maps](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467060) | [Paddle](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FResearch\u002Ftree\u002Fmaster\u002FST_DM\u002FKDD2021-SSML) | KDD\u003Cbr>2021\n| TTE | DiDi: \u003Cbr> Shenyang | HetETA | [HetETA: Heterogeneous Information Network Embedding for Estimating Time of Arrival](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403294) | [TF](https:\u002F\u002Fgithub.com\u002Fdidi\u002Fheteta) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdidi\u002Fheteta?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdidi\u002Fheteta?color=critical&style=social) | KDD\u003Cbr>2020\n| TTE | DiDi: \u003Cbr> Beijing \u003Cbr> Suzhou \u003Cbr> Shenyang | CompactETA | [CompactETA: A Fast Inference System for Travel Time Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403386) | None | KDD\u003Cbr>2020\n| TTE | GTFS | BusTr | [BusTr: Predicting Bus Travel Times from Real-Time Traffic](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403376) | None | KDD\u003Cbr>2020\n| TTE | Taiyuan \u003Cbr> Hefei \u003Cbr> Huizhou \u003Cbr> （Baidu） | BusTr | [ConSTGAT: Contextual Spatial-Temporal Graph Attention Network for Travel Time Estimation at Baidu Maps](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403320) | None | KDD\u003Cbr>2020\n| TTE | NYC \u003Cbr> IST \u003Cbr> TKY | DeepJMT | [Context-aware Deep Model for Joint Mobility and Time Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3336191.3371837) | None | WSDM 2020\n| TTE | Beijing \u003Cbr> Shanghai | TTPNet | [TTPNet: A Neural Network for Travel Time Prediction Based on Tensor Decomposition and Graph Embedding](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9261122) | [Code](https:\u002F\u002Fgithub.com\u002FYibinShen\u002FTTPNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYibinShen\u002FTTPNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYibinShen\u002FTTPNet?color=critical&style=social) | TKDE 2020\n| TTE | DiDiBJ | RNML-ETA | [Road Network Metric Learning for Estimated Time of Arrival](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9412145) | None | ICPR 2020\n| TTE | Cainiao | DeepETA | [DeepETA: A Spatial-Temporal Sequential Neural Network Model for Estimating Time of Arrival in Package Delivery System](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3856) | None | AAAI\u003Cbr>2019\n| TTE | Beijing \u003Cbr> Shanghai | CTTE | [Aggressive driving saves more time? Multi-task learning for customized travel time estimation](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0234.pdf) | None | IJCAI\u003Cbr>2019\n| TTE | Shanghai \u003Cbr> Porto | DeepI2T | [Travel time estimation without road networks: an urban morphological layout representation approach](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0245.pdf) | None | IJCAI\u003Cbr>2019\n| TTE | Porto \u003Cbr> Chengdu | DeepIST | [DeepIST: Deep Image-based Spatio-Temporal Network for Travel Time Estimation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3357870) | [TF](https:\u002F\u002Fgithub.com\u002Fcsiesheep\u002Fdeepist) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcsiesheep\u002Fdeepist?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcsiesheep\u002Fdeepist?color=critical&style=social) | CIKM\u003Cbr>2019\n| TTE | Singapore | AtHy-TNet | [Path Travel Time Estimation using Attribute-related Hybrid Trajectories Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357927) | None | CIKM\u003Cbr>2019\n| TTE | BT-Traffic \u003Cbr> PEMS07 \u003Cbr> Q-traffic | NASF | [Learning to Effectively Estimate the Travel Time for Fastest Route Recommendation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357907) | None | CIKM\u003Cbr>2019\n| TTE | Chengdu \u003Cbr> Beijing | DeepTTE | [When Will You Arrive? Estimating Travel Time Based on Deep Neural Networks](https:\u002F\u002Fjelly007.github.io\u002FdeepTTE.pdf) | [Code](https:\u002F\u002Fgithub.com\u002FUrbComp\u002FDeepTTE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUrbComp\u002FDeepTTE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUrbComp\u002FDeepTTE?color=critical&style=social) | AAAI\u003Cbr>2018\n| TTE | PORTO \u003Cbr>SANFRANCISCO | NoisyOR | [Predicting Vehicular Travel Times by Modeling Heterogeneous Influences Between Arterial Roads](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11858) | None | AAAI\u003Cbr>2018\n| TTE | MORE | MORE | [github](https:\u002F\u002Fgithub.com\u002FNickHan-cs\u002FSpatio-Temporal-Data-Mining-Survey\u002Fblob\u002Fmaster\u002FEstimated-Time-of-Arrival\u002FPaper.md) | MORE | MORE\n\n\n\n\n\u003C!--\n\n| TTE | GTFS \u003Cbr> Beijing | BusTr | [BusTr: Predicting Bus Travel Times from Real-Time Traffic](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403320) | [Code](https:\u002F\u002Fgithub.com\u002FUrbComp\u002FDeepTTE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUrbComp\u002FDeepTTE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUrbComp\u002FDeepTTE?color=critical&style=social) | AAAI\u003Cbr>2018 -->\n\n\n\n# [Traffic Location Prediction](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: |:-: | - |\n| Paper Nums:20 | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=310\u002F> |\n| Location | ETH+UCY \u003Cbr> SDD \u003Cbr> nuScenes \u003Cbr> SportVU | | [You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=POxF-LEqnF) | None | ICLR\u003Cbr>2022\n| Location | Beijing \u003Cbr> Porto | MetaPTP | [MetaPTP: An Adaptive Meta-optimized Model for Personalized Spatial Trajectory Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539360) | [Kai Zheng](http:\u002F\u002Fzheng-kai.com\u002F) Code-None | KDD\u003Cbr>2022\n| Location | BaiduApollo \u003Cbr> NGSIM | HeGA | [HeGA: Heterogeneous Graph Aggregation Network for Trajectory Prediction in High-Density Traffic](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557345) | [Code](https:\u002F\u002Fgithub.com\u002FGCDAN\u002FGCDAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGCDAN\u002FGCDAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGCDAN\u002FGCDAN?color=critical&style=social) | CIKM\u003Cbr>2022\n| Location | ETH \u003Cbr> Hotel \u003Cbr> Univ \u003Cbr> Zara1 \u003Cbr> Zara2 | SGTN | [Social Graph Transformer Networks for Pedestrian Trajectory Prediction in Complex Social Scenarios](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557455) | [Code](https:\u002F\u002Fgithub.com\u002FGCDAN\u002FGCDAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGCDAN\u002FGCDAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGCDAN\u002FGCDAN?color=critical&style=social) | CIKM\u003Cbr>2022\n| Location | Gowalla \u003Cbr> Foursquare \u003Cbr> WiFi-Trace | GCDAN | [Predicting Human Mobility via Graph Convolutional Dual-attentive Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3488560.3498400) | [Code](https:\u002F\u002Fgithub.com\u002FGCDAN\u002FGCDAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGCDAN\u002FGCDAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGCDAN\u002FGCDAN?color=critical&style=social) | WSDM 2022\n| Location | MI \u003Cbr> SIP | CMT-Net | [CMT-Net: A Mutual Transition Aware Framework for Taxicab Pick-ups and Drop-offs Co-Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3488560.3498394) | None | WSDM 2022\n| Location | Gowalla \u003Cbr> FS-NYC \u003Cbr> FS-TKY | MobTCast | [MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Ffecf2c550171d3195c879d115440ae45-Abstract.html) | [Author](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1xfiaz9cAxKYmNWgOH986JpMVSQbt3_qu?usp=sharing) | NeurIPS 2021\n| Location | ETH \u003Cbr> Hotel \u003Cbr> Univ \u003Cbr> Zara1 \u003Cbr> Zara2 | CARPe | [CARPe Posterum: A Convolutional Approach for Real-Time Pedestrian Path Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16335) | [Code](https:\u002F\u002Fgithub.com\u002FTeCSAR-UNCC\u002FCARPe_Posterum) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) | AAAI\u003Cbr>2021\n| Location | ETH \u003Cbr> Hotel \u003Cbr> Univ \u003Cbr> Zara1 \u003Cbr> Zara2 | TPNMS | [Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16299) | [Code](https:\u002F\u002Fgithub.com\u002FBlessinglrq\u002FTPNMS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBlessinglrq\u002FTPNMS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBlessinglrq\u002FTPNMS?color=critical&style=social) | AAAI\u003Cbr>2021\n| Location | ETH \u003Cbr> Hotel \u003Cbr> Univ \u003Cbr> Zara1 \u003Cbr> Zara2 | DMRGCN | [Disentangled Multi-Relational Graph Convolutional Network for Pedestrian Trajectory Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16174) | [Code](https:\u002F\u002Fgithub.com\u002FTeCSAR-UNCC\u002FCARPe_Posterum) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) | AAAI\u003Cbr>2021\n| Location | Gowalla \u003Cbr> Foursquare | BSDA | [Location Predicts You: Location Prediction via Bi-direction Speculation and Dual-level Association](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F74) | None | IJCAI\u003Cbr>2021\n| Location | ETH-UCY \u003Cbr> Collisions \u003Cbr> NGsim \u003Cbr>Charges \u003Cbr> NBA | FQA | [Multi-agent Trajectory Prediction with Fuzzy Query Attention](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Ffe87435d12ef7642af67d9bc82a8b3cd-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fnitinkamra1992\u002FFQA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnitinkamra1992\u002FFQA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnitinkamra1992\u002FFQA?color=critical&style=social) | NeurIPS 2020\n| Location | ETH-UCY \u003Cbr> Collisions \u003Cbr> NGsim \u003Cbr>Charges \u003Cbr> NBA | ARNN | [An Attentional Recurrent Neural Network for Personalized Next Location Recommendation](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5337) | None | AAAI\u003Cbr>2020\n| Location | ETH \u003Cbr> Hotel \u003Cbr> Univ \u003Cbr> Zara1 \u003Cbr> Zara2 | MDNLSTM | [Multimodal Interaction-Aware Trajectory Prediction in Crowded Space](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6874) | None | AAAI\u003Cbr>2020\n| Location | Atlantic| OMuLeT | [OMuLeT: Online Multi-Lead Time Location Prediction for Hurricane Trajectory Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5444) | [Matlab](https:\u002F\u002Fgithub.com\u002Fcqwangding\u002FOMuLeT) | AAAI\u003Cbr>2020\n| Location | Gowalla \u003Cbr> Foursquare | Flashback | [OMuLeT: Online Multi-Lead Time Location Prediction for Hurricane Trajectory Forecasting](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F302) | [Code](https:\u002F\u002Fgithub.com\u002FeXascaleInfolab\u002FFlashback_code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FeXascaleInfolab\u002FFlashback_code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FeXascaleInfolab\u002FFlashback_code?color=critical&style=social) | IJCAI\u003Cbr>2020\n| Location | CrowdCJ \u003Cbr> TrashBins \u003Cbr>B&B \u003Cbr> MYOPIC | MALMCS | [Dynamic Public Resource Allocation Based on Human Mobility Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3380986) | [Python](https:\u002F\u002Fgithub.com\u002Fsjruan\u002Fmalmcs) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsjruan\u002Fmalmcs?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsjruan\u002Fmalmcs?color=critical&style=social) | UbiComp 2020\n| Location | ETH \u003Cbr> Hotel \u003Cbr> Univ \u003Cbr> Zara1 \u003Cbr> Zara2 | Social-BiGAT | [Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fd09bf41544a3365a46c9077ebb5e35c3-Abstract.html) | None | NeurIPS 2019\n| Location | Foursquare \u003Cbr> Gowalla | VANext | [Predicting Human Mobility via Variational Attention](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313610) | None | WWW 2019\n| Location | Flickr \u003Cbr> Foursquare \u003Cbr> Geolife | CATHI | [Context-aware Variational Trajectory Encoding and Human Mobility Inference](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313608) | None | WWW 2019\n| Location | ETH \u003Cbr> Hotel \u003Cbr> Univ \u003Cbr> Zara1 \u003Cbr> Zara2 | STGAT | [STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fhtml\u002FHuang_STGAT_Modeling_Spatial-Temporal_Interactions_for_Human_Trajectory_Prediction_ICCV_2019_paper.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhuang-xx\u002FSTGAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) | ICCV 2019\n| Location | BaiduBJ | HST-LSTM | [HST-LSTM: A Hierarchical Spatial-Temporal Long-Short Term Memory Network for Location Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F324) | [Code](https:\u002F\u002Fgithub.com\u002FLogan-Lin\u002FST-LSTM_Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLogan-Lin\u002FST-LSTM_Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLogan-Lin\u002FST-LSTM_Code?color=critical&style=social) | IJCAI\u003Cbr>2018\n| Location | Foursquare \u003Cbr> MobileAPP \u003Cbr> CellularSH | DeepMove | [DeepMove: Predicting Human Mobility with Attentional Recurrent Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3178876.3186058) | [Code](https:\u002F\u002Fgithub.com\u002Fvonfeng\u002FDeepMove) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvonfeng\u002FDeepMove?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvonfeng\u002FDeepMove?color=critical&style=social) | WWW 2018\n| Location | MORE | MORE | [github](https:\u002F\u002Fgithub.com\u002Fxuehaouwa\u002FAwesome-Trajectory-Prediction) | [Hao Xue](https:\u002F\u002Fgithub.com\u002Fxuehaouwa\u002FAwesome-Trajectory-Prediction) | MORE\n| Location | MORE | MORE | [https:\u002F\u002Fgithub.com\u002FPursueee\u002FTrajectory-Paper-Collation](https:\u002F\u002Fgithub.com\u002FPursueee\u002FTrajectory-Paper-Collation) | [Code](https:\u002F\u002Fgithub.com\u002FPursueee\u002FTrajectory-Paper-Collation) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPursueee\u002FTrajectory-Paper-Collation?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FPursueee\u002FTrajectory-Paper-Collation?color=critical&style=social) | MORE\n\n\n\u003C!--\n| Location | Foursquare \u003Cbr> MobileAPP \u003Cbr> CellularSH | DeepMove | [DeepMove: Predicting Human Mobility with Attentional Recurrent Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3178876.3186058) | [Code](https:\u002F\u002Fgithub.com\u002Fvonfeng\u002FDeepMove) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvonfeng\u002FDeepMove?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvonfeng\u002FDeepMove?color=critical&style=social) | WWW 2018\n\n| Location | ETH-UCY \u003Cbr> Collisions \u003Cbr> NGsim \u003Cbr>Charges \u003Cbr> NBA | FQA | [An Attentional Recurrent Neural Network for Personalized Next Location Recommendation](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5337) | [Code](https:\u002F\u002Fgithub.com\u002Fhuang-xx\u002FSTGAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) | AAAI\u003Cbr>2020 -->\n\n\n\n\n# [Event Prediction](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums:21 | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| Event | ETT \u003Cbr> PM2.5 \u003Cbr> IndD | NsTKA | [Non-stationary Time-aware Kernelized Attention for Temporal Event Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539470) | [Future](https:\u002F\u002Fgithub.com\u002Falipay\u002Fnstka-kdd22) | KDD\u003Cbr>2022\n| Crime Prediction | Chicago Crime\u003Cbr> LA Crime\u003Cbr> | HAGEN | [HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F20338) | [Code](https:\u002F\u002Fgithub.com\u002FRafa-zy\u002FHAGEN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRafa-zy\u002FHAGEN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRafa-zy\u002FHAGEN?color=critical&style=social) | AAAI\u003Cbr>2022\n| Event | PEMS | AGWN | [Early Forecast of Traffc Accident Impact Based on a Single-Snapshot Observation (Student Abstract)](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_sa103) | [Code](https:\u002F\u002Fgithub.com\u002Fgm3g11\u002FAGWN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgm3g11\u002FAGWN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgm3g11\u002FAGWN?color=critical&style=social) | AAAI\u003Cbr>2022\n| Event | SLA-VAE \u003Cbr> E-commerce | RETE | [RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3511974) | [Code](https:\u002F\u002Fgithub.com\u002FDiMarzioBian\u002FRETE_TheWebConf) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDiMarzioBian\u002FRETE_TheWebConf?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDiMarzioBian\u002FRETE_TheWebConf?color=critical&style=social) | WWW 2022\n| Event | NYC \u003Cbr> Chicago | GSNet | [GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16566) | [Code](https:\u002F\u002Fgithub.com\u002FEchohhhhhh\u002FGSNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEchohhhhhh\u002FGSNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEchohhhhhh\u002FGSNet?color=critical&style=social) | AAAI\u003Cbr>2021\n| Event | NYCIncidents \u003Cbr> CHIIncidents \u003Cbr> SFIncidents | STCGNN | [Spatio-Temporal-Categorical Graph Neural Networks for Fine-Grained Multi-Incident Co-Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482482) | [Code](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FSTC-GNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FSTC-GNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FSTC-GNN?color=critical&style=social) | CIKM\u003Cbr>2021\n| Event | Thailand \u003Cbr> Egypt \u003Cbr> India \u003Cbr>Russia \u003Cbr> Covid-19 | CMF | [Understanding Event Predictions via Contextualized Multilevel Feature Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482309) | None | CIKM\u003Cbr>2021\n| Event Prediction | DJIA30 \u003Cbr> WebTraffic \u003Cbr> NetFlow \u003Cbr> ClockErr \u003Cbr> AbServe | EvoNet | [Time-Series Event Prediction with Evolutionary State Graph](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441827) | [tf](https:\u002F\u002Fgithub.com\u002FVachelHU\u002FEvoNet) | WSDM 2021\n| Event | NYCIncidents \u003Cbr> CHIIncidents \u003Cbr> SFIncidents | PreView | [Dynamic Heterogeneous Graph Neural Network for Real-time Event Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403373) | None | KDD\u003Cbr>2020\n| Event Prediction | MIMIC-III | DSSM | [Deep State-Space Generative Model For Correlated Time-to-Event Predictions](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403206) | None | KDD\u003Cbr>2020\n| Event | Beijing \u003Cbr> Suzhou \u003Cbr> Shenyang | RiskOracle | [RiskOracle: A Minute-Level Citywide Traffic Accident Forecasting Framework](https:\u002F\u002Fojs.aaai.org\u002F\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5480) | [TF](https:\u002F\u002Fgithub.com\u002Fzzyy0929\u002FAAAI2020-RiskOracle\u002F) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzzyy0929\u002FAAAI2020-RiskOracle\u002F?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzzyy0929\u002FAAAI2020-RiskOracle\u002F?color=critical&style=social) | AAAI\u003Cbr>2020\n| Event | NYCIncidents \u003Cbr> CHIIncidents | STrans | [Hierarchically Structured Transformer Networks for Fine-Grained Spatial Event Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380296) | None | WWW 2020\n| Event | FewEvent | DMB-PN | [Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3336191.3371796) | [dataset](https:\u002F\u002Fgithub.com\u002F231sm\u002FLow_Resource_KBP) | WSDM 2020\n| Event | NYC \u003Cbr> SIP | RiskSeq | [Foresee Urban Sparse Traffic Accidents: A Spatiotemporal Multi-Granularity Perspective](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9242313) | None| TKDE 2020\n| Event | MemeTracker \u003Cbr> Weibo | LANTERN | [Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fa29d1598024f9e87beab4b98411d48ce-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fzhangzx-sjtu\u002FLANTERN-NeurIPS-2019) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhangzx-sjtu\u002FLANTERN-NeurIPS-2019?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhangzx-sjtu\u002FLANTERN-NeurIPS-2019?color=critical&style=social) | NeurIPS 2019\n| Event | Graph \u003Cbr> Stack \u003Cbr> SmartHome \u003Cbr> CarIndicators | WGP-LN, \u003Cbr> FD-Dir | [Uncertainty on Asynchronous Time Event Prediction](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F78efce208a5242729d222e7e6e3e565e-Abstract.html) | [TF](https:\u002F\u002Fgithub.com\u002Fsharpenb\u002FUncertainty-Event-Prediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsharpenb\u002FUncertainty-Event-Prediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsharpenb\u002FUncertainty-Event-Prediction?color=critical&style=social) | NeurIPS 2019\n| Event | Thailand \u003Cbr> Egypt \u003Cbr> India \u003Cbr>Russia | DynamicGCN | [Learning Dynamic Context Graphs for Predicting Social Events](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330919) | [Code](https:\u002F\u002Fgithub.com\u002Famy-deng\u002FDynamicGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) | KDD\u003Cbr>2019\n| Event | NYCCollision \u003Cbr> ChicagoCrime \u003Cbr> NYCTaxi | DMPP | [Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Information](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330937) | None | KDD\u003Cbr>2019\n| Event | Civil \u003Cbr> Air Quality | SIMDA | [Incomplete Label Multi-Task Deep Learning for Spatio-Temporal Event Subtype Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4245) | None | AAAI\u003Cbr>2019\n| Crime Prediction | NYC Crime \u003Cbr> NYC Anomaly \u003Cbr> Chicago Crime | MiST | [MiST: A Multiview and Multimodal Spatial-Temporal Learning Framework for Citywide Abnormal Event Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313730) | None | WWW 2019\n| Event | NYCAccident \u003Cbr> NYCEvent | DFN | [Deep Dynamic Fusion Network for Traffic Accident Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357829) | None | CIKM\u003Cbr>2019\n| Event | | Hetero-ConvLSTM | [Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9242313) | None| KDD\u003Cbr>2018\n\n\n\n\n\n\u003C!--\n| Event | NYCIncidents \u003Cbr> CHIIncidents | PreView | [Hierarchically Structured Transformer Networks for Fine-Grained Spatial Event Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380296) | [Code](https:\u002F\u002Fgithub.com\u002Famy-deng\u002FDynamicGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) | WWW 2020 -->\n\n\n\n\n# [Stock Prediction](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums:30+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| Stock Price \u003Cbr> Prediction | NASDAQ \u003Cbr> NYSE \u003Cbr> S&P500 | StockMixer | [StockMixer: A Simple Yet Strong MLP-Based Architecture for Stock Price Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28681) | [Code](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FStockMixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FStockMixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FStockMixer?color=critical&style=social) | AAAI\u003Cbr>2024\n| Stock Price \u003Cbr> Prediction | CSI 300 \u003Cbr> CSI 800 | MASTER | [MASTER: Market-Guided Stock Transformer for Stock Price Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F27767) | [Code](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FMASTER) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FMASTER?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FMASTER?color=critical&style=social) | AAAI\u003Cbr>2024\n| Stock Movement \u003Cbr> Prediction | Qin \u003Cbr> MAEC | ECHO-GL | [ECHO-GL: Earnings Calls-Driven Heterogeneous Graph Learning for Stock Movement Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29305) | [Code](https:\u002F\u002Fgithub.com\u002Fpupu0302\u002FECHOGL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpupu0302\u002FECHOGL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpupu0302\u002FECHOGL?color=critical&style=social) | AAAI\u003Cbr>2024\n| Stock Trend \u003Cbr> Prediction | CSI 300 \u003Cbr> CSI 500 | DoubleAdapt | [DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599315) | [Code](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FDoubleAdapt) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FDoubleAdapt?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FDoubleAdapt?color=critical&style=social) | KDD\u003Cbr>2023\n| Stock Movement \u003Cbr> Prediction | ACL18 \u003Cbr> DJIA | PEN | [PEN: Prediction-Explanation Network to Forecast Stock Price Movement with Better Explainability](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25648) | [TF](https:\u002F\u002Fgithub.com\u002FShuqi-li\u002FPEN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FShuqi-li\u002FPEN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FShuqi-li\u002FPEN?color=critical&style=social) | AAAI\u003Cbr>2023\n| Stock \u003Cbr> Prediction | NASDAQ \u003Cbr> NYSE \u003Cbr> CSI | RT-GCN | [Relational Temporal Graph Convolutional Networks for Ranking-Based Stock Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184655) | [Code](https:\u002F\u002Fgithub.com\u002Fzhengzetao\u002FRTGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhengzetao\u002FRTGCNt?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhengzetao\u002FRTGCN?color=critical&style=social) | ICDE 2023\n| Stock Movement \u003Cbr> Prediction | S&P 500 | ESTIMATE | [Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570427) | [Code](https:\u002F\u002Fgithub.com\u002Fthanhtrunghuynh93\u002Festimate) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthanhtrunghuynh93\u002Festimate?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthanhtrunghuynh93\u002Festimate?color=critical&style=social) | WSDM 2023\n| Stock Price \u003Cbr> Prediction | ACL18 | D-va | [Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614844) | [Gluonts](https:\u002F\u002Fgithub.com\u002Fkoa-fin\u002Fdva) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkoa-fin\u002Fdva?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkoa-fin\u002Fdva?color=critical&style=social) | CIKM\u003Cbr>2023\n| Stock Price \u003Cbr> Prediction | CSI 300 \u003Cbr> CSI 500 \u003Cbr> CSI 800 | CISP | [Follow the Will of the Market: A Context-Informed Drift-Aware Method for Stock Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614886) | None | CIKM\u003Cbr>2023\n| Stock Movement \u003Cbr> Prediction | Calls | NumHTML | [NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-task Financial Forecasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai4799) | [Future,Author](https:\u002F\u002Fgithub.com\u002FYangLinyi) | AAAI\u003Cbr>2022\n| Stock Prediction | NASDAQ \u003Cbr> NYSE \u003Cbr> TSE | ALSP-TF | [Adaptive Long-Short Pattern Transformer for Stock Investment Selection](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F551) | None | IJCAI\u003Cbr>2022\n| Stock Prediction | S&P 500 \u003Cbr> Ashare&HK | HISN | [Heterogeneous Interactive Snapshot Network for Review-Enhanced Stock Profiling and Recommendation](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F550) | None | IJCAI\u003Cbr>2022\n| Stock \u003Cbr> Prediction | S&P500 \u003Cbr> CSI300 \u003Cbr> Twitter | THGNN | [Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557089) | None | CIKM\u003Cbr>2022\n| Stock \u003Cbr> Prediction | CSI800 | PASN | [Pattern Adaptive Specialist Network for Learning Trading Patterns in Stock Market](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557665) | None | CIKM\u003Cbr>2022\n| Stock Movement\u003Cbr> Prediction | NASDAQ \u003Cbr> Bitcoin | KHIT | [Kernel-based Hybrid Interpretable Transformer for High-frequency Stock Movement Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027785) | None | ICDM 2022\n| Stock Movement\u003Cbr> Prediction | CSI800 | TRA | [Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467358) | [Code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks\u002FTRA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks\u002FTRA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks\u002FTRA?color=critical&style=social) | KDD\u003Cbr>2021\n| Stock Movement \u003Cbr> Prediction | ACL18 \u003Cbr> KDD17 \u003Cbr> NDX100 \u003Cbr> CSI300 \u003Cbr> NI225\u003Cbr> FTSE100 | DTML | [Accurate Multivariate Stock Movement Prediction via Data-Axis Transformer with Multi-Level Contexts](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467297) | None| KDD\u003Cbr>2021\n| Stock \u003Cbr> Prediction | Self-defined | AD-GAT | [Modeling the Momentum Spillover Effect for Stock Prediction via Attribute-Driven Graph Attention Networks](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16077) | [Code](https:\u002F\u002Fgithub.com\u002FRuichengFIC\u002FADGAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRuichengFIC\u002FADGAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRuichengFIC\u002FADGAT?color=critical&style=social) | AAAI\u003Cbr>2021\n| Stock Selection | NASDAQ \u003Cbr> NYSE \u003Cbr> TSE| STHAN-SR | [Stock Selection via Spatiotemporal Hypergraph Attention Network: A Learning to Rank Approach](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16127) | None | AAAI\u003Cbr>2021\n| Stock Movement\u003Cbr> Prediction | TPX500 | CGM | [Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0518.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Flancopku\u002FCGM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flancopku\u002FCGM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flancopku\u002FCGM?color=critical&style=social) | IJCAI\u003Cbr>2021\n| Stock Trend\u003Cbr> Prediction | CSI300 \u003Cbr> SPX \u003Cbr> TOPIX-100 | HATR | [Hierarchical Adaptive Temporal-Relational Modeling for Stock Trend Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0508.pdf) | None | IJCAI\u003Cbr>2021\n| Stock Movement\u003Cbr> Prediction | NASDAQ \u003Cbr> NYSE \u003Cbr> TSE \u003Cbr> China & HK | HyperStockGAT | [Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450095) | None| WWW 2021\n| Stock Trend\u003Cbr> Prediction | CSI300 \u003Cbr> CSI500 | REST | [REST: Relational Event-driven Stock Trend Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450032) | None | WWW 2021\n| Stock Trend \u003Cbr> Prediction | CSI300 \u003Cbr> CSI800 \u003Cbr> NASDAQ100| CMLF | [Stock Trend Prediction with Multi-granularity Data: A Contrastive Learning Approach with Adaptive Fusion](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482483) | [Code](https:\u002F\u002Fgithub.com\u002FCMLF-git-dev\u002FCMLF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCMLF-git-dev\u002FCMLF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCMLF-git-dev\u002FCMLF?color=critical&style=social) | CIKM\u003Cbr>2021\n| Stock Movement \u003Cbr> Prediction | Self-defined | MFN | [Incorporating Expert-Based Investment Opinion Signals in Stock Prediction: A Deep Learning Framework](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5445) | None | AAAI\u003Cbr>2020\n| Stock Movement \u003Cbr> Prediction | TPX500 \u003Cbr> TPX100 | LSTM-RGCN | [Modeling the Stock Relation with Graph Network for Overnight Stock Movement Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0626.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Fliweitj47\u002Fovernight-stock-movement-prediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliweitj47\u002Fovernight-stock-movement-prediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliweitj47\u002Fovernight-stock-movement-prediction?color=critical&style=social) | IJCAI\u003Cbr>2020\n| Stock Movement \u003Cbr> Prediction | NASDAQ \u003Cbr> ChinaAShare | HMG-TF | [Hierarchical Multi-Scale Gaussian Transformer for Stock Movement Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0640.pdf) | None | IJCAI\u003Cbr>2020\n| Stock Trend\u003Cbr> Prediction | FI-2010 \u003Cbr> CSI-2016 | MTDNN | [Multi-scale Two-way Deep Neural Network for Stock Trend Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0628.pdf) | [Future](https:\u002F\u002Fgithub.com\u002Fmarscrazy\u002FMTDNN) | IJCAI\u003Cbr>2020\n| Stock Price \u003Cbr> Forecasting | Self-defined | Dandelion | [Domain adaptive multi-modality neural attention network for financial forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380288) | [Sklearn](https:\u002F\u002Fgithub.com\u002FLeo02016\u002FDandelion) | WWW 2020\n| Stock Volatility \u003Cbr> Forecasting | Calls | HTML | [Hierarchical Transformer-based Multi-task Learning for Volatility Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380128) | [Code](https:\u002F\u002Fgithub.com\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction?color=critical&style=social) | WWW 2020\n| Quantitative \u003Cbr> Investments | Self-defined | KGEEF | [Knowledge Graph-based Event Embedding Framework for Financial Quantitative Investments](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3397271.3401427) | None | SIGIR 2020\n| Stock Price \u003Cbr> Prediction | TAQ | GARCH-LSTM | [Price Forecast with High-Frequency Finance Data: An Autoregressive Recurrent Neural Network Model with Technical Indicators](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3412738) | None | CIKM\u003Cbr>2020\n| Stock Movement \u003Cbr> Prediction | HATS | STHGCN | [Spatiotemporal hypergraph convolution network for stock movement forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338303) | [Code](https:\u002F\u002Fgithub.com\u002Fmidas-research\u002Fsthgcn-icdm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmidas-research\u002Fsthgcn-icdm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmidas-research\u002Fsthgcn-icdm?color=critical&style=social) | ICDM 2020\n| Stock Market \u003Cbr> Prediction | Nikkei | GNNs | [Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.10660) | None | NeurIPSw 2019\n| Stock Trend \u003Cbr> Prediction | ChineseStock | IMTR | [Investment Behaviors Can Tell What Inside: Exploring Stock Intrinsic Properties for Stock Trend Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330663) | None| KDD\u003Cbr>2019\n| Stock Movement \u003Cbr> Prediction | CSI200 \u003Cbr> CSI300 \u003Cbr> CSI500 | RNN-MRFs | [Multi-task Recurrent Neural Networks and Higher-order Markov Random Fields for Stock Price Movement Prediction: Multi-task RNN and Higer-order MRFs for Stock Price Classification](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330983) | None | KDD\u003Cbr>2019\n| Stock Movement \u003Cbr> Prediction | Self-defined | TTIO | [Individualized Indicator for All: Stock-wise Technical Indicator Optimization with Stock Embedding](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330833) | None | KDD\u003Cbr>2019\n| Stock Movement \u003Cbr> Prediction | ACL18 \u003Cbr> KDD17 \u003Cbr> NDX100 \u003Cbr> CSI300 \u003Cbr> NI225\u003Cbr> FTSE100| Adv-ALSTM | [Enhancing stock movement prediction with adversarial training](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0810.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Ffulifeng\u002FAdv-ALSTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffulifeng\u002FAdv-ALSTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ffulifeng\u002FAdv-ALSTM?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Stock Prediction | NASDAQ \u003Cbr> NYSE | RSR | [Temporal Relational Ranking for Stock Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330833) | [TF](https:\u002F\u002Fgithub.com\u002Ffulifeng\u002FTemporal_Relational_Stock_Ranking) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffulifeng\u002FTemporal_Relational_Stock_Ranking?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ffulifeng\u002FTemporal_Relational_Stock_Ranking?color=critical&style=social) | TOIS 2019\n| Stock Movement \u003Cbr> Prediction | Self-defined | StockNet | [Stock Movement Prediction from Tweets and Historical Prices](https:\u002F\u002Faclanthology.org\u002FP18-1183) | [TF](https:\u002F\u002Fgithub.com\u002Fyumoxu\u002Fstocknet-code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyumoxu\u002Fstocknet-code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyumoxu\u002Fstocknet-code?color=critical&style=social) | ACL 2018\n| Stock Trend \u003Cbr> Prediction | Self-defined | HAN | [Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3159652.3159690) | [TF](https:\u002F\u002Fgithub.com\u002Fdonghyeonk\u002Fhan) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdonghyeonk\u002Fhan?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdonghyeonk\u002Fhan?color=critical&style=social) | WSDM 2018\n| Stock Price \u003Cbr> Prediction | Self-defined | SFM | [Stock Price Prediction via Discovering Multi-Frequency Trading Patterns](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3097983.3098117) | [Keras](https:\u002F\u002Fgithub.com\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction?color=critical&style=social) | KDD\u003Cbr>2017\n| Stock Movement \u003Cbr> Prediction | NASDAQ \u003Cbr> NYSE | KGEB-CNN | [Knowledge-Driven Event Embedding for Stock Prediction](https:\u002F\u002Faclanthology.org\u002FC16-1201) | None | COLING 2016\n\n\n\n\n\n\n\n# [Other Forecasting](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums:40+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| Water Temperature \u003Cbr> Prediction | Delaware \u003Cbr> River Basin | SR-MTL | [Meta-Transfer-Learning for Time Series Data with Extreme Events: An Application to Water Temperature Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3614966) | None | CIKM\u003Cbr>2023\n| Telecommunication \u003Cbr> Traffic \u003Cbr> Forecasting | Milan (MI) \u003Cbr> Trentino (TN) | TMLM | [Telecommunication Traffic Forecasting via Multi-task Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570440) | [Author](https:\u002F\u002Fgithub.com\u002Fgpxlcj) | WSDM 2022\n| Bitcoin \u003Cbr> Volatility \u003Cbr> Forecasting | Twitter | D-TCN\t | [Ask \"Who\", Not \"What\": Bitcoin Volatility Forecasting with Twitter Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570387) | [TF](https:\u002F\u002Fgithub.com\u002Fmeakbiyik\u002Fask-who-not-what) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmeakbiyik\u002Fask-who-not-what?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmeakbiyik\u002Fask-who-not-what?color=critical&style=social) | WSDM 2022\n| Rating \u003Cbr> Migration \u003Cbr> Prediction | Self | META | [Multi-task Envisioning Transformer-based Autoencoder for Corporate Credit Rating Migration Early Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539098) | None | KDD\u003Cbr>2022\n| COVID-19 \u003Cbr> Prediction | TokyoCOVID19 | SAB-GNN | [Multiwave COVID-19 Prediction from Social Awareness Using Web Search and Mobility Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539172) | [Code](https:\u002F\u002Fgithub.com\u002FJiaweiXue\u002FMultiwaveCovidPrediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJiaweiXue\u002FMultiwaveCovidPrediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJiaweiXue\u002FMultiwaveCovidPrediction?color=critical&style=social) | KDD\u003Cbr>2022\n| Service \u003Cbr> Time \u003Cbr> Prediction | DowBJ \u003Cbr> SubBJ | MetaSTP | [Service Time Prediction for Delivery Tasks via Spatial Meta-Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539027) | None | KDD\u003Cbr>2022\n| Physician \u003Cbr> Burnout \u003Cbr> Prediction | EHR \u003Cbr> Burnout | HiPAL | [HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539056) | [TF](https:\u002F\u002Fgithub.com\u002FHanyangLiu\u002FHiPAL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHanyangLiu\u002FHiPAL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHanyangLiu\u002FHiPAL?color=critical&style=social) | KDD\u003Cbr>2022\n| Crop Yield Prediction | American Crop | GNN-RNN | [A GNN-RNN Approach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aisi6416) | None | AAAI\u003Cbr>2022\n| Epidemic Prediction | Globe \u003Cbr> US-State \u003Cbr> US-County | CausalGNN | [CausalGNN: Causal-based Graph Neural Networks for Spatio-Temporal](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aisi6475) | Future | AAAI\u003Cbr>2022\n| Soil Moisture \u003Cbr> Forecasting | Spain \u003Cbr> USA | DGLR | [Dynamic Structure Learning through Graph Neural Network for Forecasting Soil Moisture in Precision Agriculture](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F720) | [Code](https:\u002F\u002Fgithub.com\u002FAnoushkaVyas\u002FDGLR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAnoushkaVyas\u002FDGLR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAnoushkaVyas\u002FDGLR?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Disease Prediction | Disease \u003Cbr> Tumors | PopNet | [PopNet: Real-Time Population-Level Disease Prediction with Data Latency](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512127) | [Code](https:\u002F\u002Fgithub.com\u002Fv1xerunt\u002FPopNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fv1xerunt\u002FPopNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fv1xerunt\u002FPopNet?color=critical&style=social) | WWW 2022\n| FakeNews Detection | Snop \u003Cbr> PolitiFact | GET | [Evidence-aware Fake News Detection with Graph Neural Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512122) | [Keras](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FGET) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCRIPAC-DIG\u002FGET?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCRIPAC-DIG\u002FGET?color=critical&style=social) | WWW 2022\n| Crime Prediction | NYC \u003Cbr> Chicago | ST-HSL | [Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835423) | [Code](https:\u002F\u002Fgithub.com\u002FLZH-YS1998\u002FSTHSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLZH-YS1998\u002FSTHSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLZH-YS1998\u002FSTHSL?color=critical&style=social) | ICDE 2022\n| Popularity \u003Cbr> Prediction | WbTopic \u003Cbr> WbRepost \u003Cbr> Twitter | HERI-GCN | [Deep Popularity Prediction in Multi-Source Cascade with HERI-GCN](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835455) | [Code](https:\u002F\u002Fgithub.com\u002FLes1ie\u002FHERI-GCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLes1ie\u002FHERI-GCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLes1ie\u002FHERI-GCN?color=critical&style=social) | ICDE 2022\n| Parking Pricing | SFMTA \u003Cbr> SDOT | None | [Prediction-based One-shot Dynamic Parking Pricing](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557421) | None| CIKM\u003Cbr>2022\n| Future Citation | APS \u003Cbr> AMiner | DGNI | [Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557398) | None| CIKM\u003Cbr>2022\n| Pandemic Forecasting | Large-MG | HiSTGNN | [Hierarchical Spatio-Temporal Graph Neural Networks for Pandemic Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557350) | None| CIKM\u003Cbr>2022\n| Search Traffic \u003Cbr> Forecasting | M5 \u003Cbr> FGSF \u003Cbr> SQTE | STARDOM | [STARDOM: Semantic Aware Deep Hierarchical Forecasting Model for Search Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557102) | None| CIKM\u003Cbr>2022\n| Crime Prediction | NYC \u003Cbr> Chicago | LTFMs | [Locality Aware Temporal FMs for Crime Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557657) | None| CIKM\u003Cbr>2022\n| Energy Markets | Nordpool | None | [A Graph-based Spatiotemporal Model for Energy Markets](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557530) | None| CIKM\u003Cbr>2022\n| Denoised Health \u003Cbr> Risk Prediction | EHR | MedSkim | [MedSkim: Denoised Health Risk Prediction via Skimming Medical Claims Data](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027678) | [Code](https:\u002F\u002Fgithub.com\u002FSH-Src\u002FMedSkim) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSH-Src\u002FMedSkim?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSH-Src\u002FMedSkim?color=critical&style=social) | ICDM 2022\n| Demand \u003Cbr> Prediction | E-Commerce \u003Cbr> M5 | Forchestra | [A Large-Scale Ensemble Learning Framework for Demand Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027662) | [Code](https:\u002F\u002Fgithub.com\u002Fyoung-j-park\u002F22-ICDM-Forchestra) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyoung-j-park\u002F22-ICDM-Forchestra?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyoung-j-park\u002F22-ICDM-Forchestra?color=critical&style=social) | ICDM 2022\n| Transfer \u003Cbr> Traffic Flow \u003Cbr> Prediction | ShanghaiBIKE \u003Cbr> NanjingBus \u003Cbr> HaikouDiDi | CCMHC | [Exploiting Hierarchical Correlations for Cross-City Cross-Mode Traffic Flow Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027729) | [Code](https:\u002F\u002Fgithub.com\u002Fchenyan89\u002FCCMHC) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenyan89\u002FCCMHC?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenyan89\u002FCCMHC?color=critical&style=social) | ICDM 2022\n| Precipitation \u003Cbr> Nowcasting | ERA5 \u003Cbr> WeatherBench | SCC-ConvLSTM | [Spatiotemporal Contextual Consistency Network for Precipitation Nowcasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027644) | [Future](https:\u002F\u002Fgithub.com\u002FEricKing19\u002FSCCN) | ICDM 2022\n| Transfer \u003Cbr> Traffic Flow \u003Cbr> Prediction | Shenzhen \u003Cbr> HB \u003Cbr> Chengdu \u003Cbr> Xian | Mest-GAN | [Mest-GAN: Cross-City Urban Traffic Estimation with Meta Spatial-Temporal Generative Adversarial Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027789) | None | ICDM 2022\n| Transfer \u003Cbr> Human Mobility \u003Cbr> Prediction | Houston \u003Cbr> Iowa City | STORM-GAN | [STORM-GAN: Spatio-Temporal Meta-GAN for Cross-City Estimation of Human Mobility Responses to COVID-19](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027783) | [Code](https:\u002F\u002Fgithub.com\u002FBaoHan88\u002FSTROM-GAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBaoHan88\u002FSTROM-GAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBaoHan88\u002FSTROM-GAN?color=critical&style=social) | ICDM 2022\n| Transfer \u003Cbr> Traffic Flow \u003Cbr> Prediction | Shenzhen \u003Cbr> HB \u003Cbr> Chengdu \u003Cbr> Xian | STrans-GAN | [STrans-GAN: Spatially-Transferable Generative Adversarial Networks for Urban Traffic Estimation](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027643) | None | ICDM 2022\n| Churn Prediction | Beidian \u003Cbr> Epinions | CFChurn | [A Counterfactual Modeling Framework for Churn Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3488560.3498468) | [Code](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FCFChurn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FCFChurn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FCFChurn?color=critical&style=social) | WSDM 2022\n| Streaming \u003Cbr> Traffic Flow | PEMS03 | TrafficStream | [TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F498\u002F) | [Code](https:\u002F\u002Fgithub.com\u002FAprLie\u002FTrafficStream) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAprLie\u002FTrafficStream?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAprLie\u002FTrafficStream?color=critical&style=social) | IJCAI\u003Cbr>2021\n| Crime \u003Cbr> Prediction | NYC \u003Cbr> Chicago | ST-SHN | [Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0225.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FST-SHN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fakaxlh\u002FST-SHN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fakaxlh\u002FST-SHN?color=critical&style=social) | IJCAI\u003Cbr>2021\n| Purchase Intent Forecasting | JD-e-commerce | CHTR | [Purchase Intent Forecasting with Convolutional Hierarchical Transformer Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458836) | None | ICDE 2021\n| Popularity Prediction | Tmall | ATNN | [Adversarial Two-Tower Neural Network for New Item’s Popularity Prediction in E-commerce](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458869) | None | ICDE 2021\n| Career Trajectory Prediction | Company \u003Cbr> Position | TACTP | [Variable Interval Time Sequence Modeling for Career Trajectory Prediction: Deep Collaborative Perspective](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3442381.3449959) | None | WWW 2021\n| Health Prediction | NASH \u003Cbr> AD | UNITE | [UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450087) | [Code](https:\u002F\u002Fgithub.com\u002FChacha-Chen\u002FUNITE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChacha-Chen\u002FUNITE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FChacha-Chen\u002FUNITE?color=critical&style=social) | WWW 2021\n| COVID-19 Forecasting | JHUCSSE | HierST | [HierST: A Unified Hierarchical Spatial-temporal Framework for COVID-19 Trend Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3481927) | [Code](https:\u002F\u002Fgithub.com\u002Fdolphin-zs\u002FHierST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdolphin-zs\u002FHierST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdolphin-zs\u002FHierST?color=critical&style=social) | CIKM\u003Cbr>2021\n| Failure Prediction | Water Pipe \u003Cbr> Sewer Pipe | FP | [Failure Prediction for Large-scale Water Pipe Networks Using GNN and Temporal Failure Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3481918) | None | CIKM\u003Cbr>2021\n| Publication Prediction | CSJ \u003Cbr> CSC | VPALG | [VPALG: Paper-publication Prediction with Graph Neural Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482490) | None | CIKM\u003Cbr>2021\n| Water Quality Prediction | | PDE-DGN | [Partial Differential Equation Driven Dynamic Graph Networks for Predicting Stream Water Temperature](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679188) | None | ICDM 2021\n| Risk Prediction | COPD \u003Cbr> HeartFailure \u003Cbr> KidneyDiseases | HiTANet | [HiTANet: Hierarchical Time-Aware Attention Networks for Risk Prediction on Electronic Health Records](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403107) | [Code](https:\u002F\u002Fgithub.com\u002FHiTANet2020\u002FHiTANet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHiTANet2020\u002FHiTANet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHiTANet2020\u002FHiTANet?color=critical&style=social) | KDD\u003Cbr>2020\n| Sales Prediction | anonymized | CARNN | [Attention based Multi-Modal New Product Sales Time-series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403362) | [Code](https:\u002F\u002Fgithub.com\u002FHumaticsLAB\u002FAttentionBasedMultiModalRNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHumaticsLAB\u002FAttentionBasedMultiModalRNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHumaticsLAB\u002FAttentionBasedMultiModalRNN?color=critical&style=social) | KDD\u003Cbr>2020\n| Economy Prediction | IRS | AMCN | [Attentional Multi-graph Convolutional Network for Regional Economy Prediction with Open Migration Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403273) | None | KDD\u003Cbr>2020\n| Food Demand | Ele.me | OFCT | [Order Fulfillment Cycle Time Estimation for On-Demand Food Delivery](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403307) | None | KDD\u003Cbr>2020\n| Parking Prediction | Beijing \u003Cbr> Shanghai | SHARE | [Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5471) | [Code](https:\u002F\u002Fgithub.com\u002FVvrep\u002FSHARE-parking_availability_prediction-Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVvrep\u002FSHARE-parking_availability_prediction-Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVvrep\u002FSHARE-parking_availability_prediction-Code?color=critical&style=social) | AAAI\u003Cbr>2020\n| Mortality Risk Prediction| MIMIC-III \u003Cbr> eICU | DATA-GRU | [DATA-GRU: Dual-Attention Time-Aware Gated Recurrent Unit for Irregular Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5440) | None | AAAI\u003Cbr>2020\n| Parking Prediction | Ningbo \u003Cbr> Changsha | PewLSTM | [PewLSTM: Periodic LSTM with Weather-Aware Gating Mechanism for Parking Behavior Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F610) | [Code](https:\u002F\u002Fgithub.com\u002FNingxuanFeng\u002FPewLSTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNingxuanFeng\u002FPewLSTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNingxuanFeng\u002FPewLSTM?color=critical&style=social) | IJCAI\u003Cbr>2020\n| Health Risk Prediction | MIMIC-III \u003Cbr> ESRD | StageNet | [StageNet: Stage-Aware Neural Networks for Health Risk Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380136) | [Code](https:\u002F\u002Fgithub.com\u002Fv1xerunt\u002FStageNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fv1xerunt\u002FStageNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fv1xerunt\u002FStageNet?color=critical&style=social) | WWW 2020\n| Micro-video Popularity Prediction | Xigua | MMVED | [A Multimodal Variational Encoder-Decoder Framework for Micro-video Popularity Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380004) | [TF](https:\u002F\u002Fgithub.com\u002Fyaochenzhu\u002FMMVED) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyaochenzhu\u002FMMVED?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyaochenzhu\u002FMMVED?color=critical&style=social) | WWW 2020\n| Drug Demand Prediction | Wikipedia | | [Predicting Drug Demand with Wikipedia Views: Evidence from Darknet Markets](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380022) | None | WWW 2020\n| Epidemic Prediction | IDWR \u003Cbr> CDC \u003Cbr> US-HHS | Cola-GNN | [Cola-GNN: Cross-location Attention based Graph Neural Networks for Long-term ILI Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411975) | [Code](https:\u002F\u002Fgithub.com\u002Famy-deng\u002Fcolagnn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famy-deng\u002Fcolagnn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famy-deng\u002Fcolagnn?color=critical&style=social) | CIKM\u003Cbr>2020\n| Risk Prediction | HeartFailure \u003Cbr> KidneyDisease \u003Cbr> Dementia | LSAN | [LSAN: Modeling Long-term Dependencies and Short-term Correlations with Hierarchical Attention for Risk Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411864) | [Code](https:\u002F\u002Fgithub.com\u002Fdmmlprojs\u002Flsan) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdmmlprojs\u002Flsan?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdmmlprojs\u002Flsan?color=critical&style=social) | CIKM\u003Cbr>2020\n| Lightning Prediction | Lightning | HSTN | [A Heterogeneous Spatiotemporal Network for Lightning Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338411) | [Future](https:\u002F\u002Fgithub.com\u002Fgyla1993\u002FHSTN) | ICDM 2020\n| Disease Prediction | mPower | RNNODE | [Predicting Parkinson’s Disease with Multimodal Irregularly Collected Longitudinal Smartphone Data](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338417) | None | ICDM 2020\n| Turbulence Prediction | Turbulence | T^2-Net | [T^2-Net: A Semi-Supervised Deep Model for Turbulence Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9338418) | None | ICDM 2020\n| Popularity Prediction | Sina Weibo | CoupledGNN | [Popularity Prediction on Social Platforms with Coupled Graph Neural Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3336191.3371834) | [TF](https:\u002F\u002Fgithub.com\u002FCaoQi92\u002FCoupledGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCaoQi92\u002FCoupledGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCaoQi92\u002FCoupledGNN?color=critical&style=social) | WSDM 2020\n| Job Mobility Prediction | Self | HCPNN | [A Hierarchical Career-Path-Aware Neural Network for Job Mobility Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330969) | [Python](https:\u002F\u002Fgithub.com\u002Fqingxin-meng\u002Fhierarchical-career-path-aware-network) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fqingxin-meng\u002Fhierarchical-career-path-aware-network?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fqingxin-meng\u002Fhierarchical-career-path-aware-network?color=critical&style=social) | KDD\u003Cbr>2019\n| Lightning Prediction | Lightning | LightNet | [LightNet: A Dual Spatiotemporal Encoder Network Model for Lightning Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330717) | [Keras](https:\u002F\u002Fgithub.com\u002Fgyla1993\u002FLightNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgyla1993\u002FLightNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgyla1993\u002FLightNet?color=critical&style=social) | KDD\u003Cbr>2019\n| Diagnosis Prediction | MIMICIII | MNN | [MNN: Multimodal Attentional Neural Networks for Diagnosis Prediction](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F823) | None | IJCAI\u003Cbr>2019\n| Crime Prediction | CrimeCHI \u003Cbr> CrimeNYC | NN-CCRF | [Neural Network based Continuous Conditional Random Field for Fine-grained Crime Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F577) | None | IJCAI\u003Cbr>2019\n| Talent Flow Forecasting | OPNs | ETF | [Large-Scale Talent Flow Forecast with Dynamic Latent Factor Model?](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313525) | None | WWW 2019\n| Sales Prediction | Snack \u003Cbr> PG&U | DSF | [A Deep Neural Framework for Sales Forecasting in E-Commerce](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357883) | None | CIKM\u003Cbr>2019\n| Load Prediction | Charging Stations | HCFN | [Heterogeneous Components Fusion Network for Load Forecasting of Charging Stations](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3358073) | None | CIKM\u003Cbr>2019\n| Mortality Risk Prediction | PUB \u003Cbr> MIMIC-III | UA-CRNN | [UA-CRNN: Uncertainty-Aware Convolutional Recurrent Neural Network for Mortality Risk Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357884) | None | CIKM\u003Cbr>2019\n| House Price Prediction | NYCHouse \u003Cbr> BJHouse | FTD_DenseNet | [An Integrated Model for Urban Subregion House Price Forecasting: A Multi-source Data Perspective](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970751) | None | ICDM 2019\n| Water Quality Prediction | | TC | [Predicting Water Quality for the Woronora Delivery Network with Sparse Samples](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970721) | None | ICDM 2019\n\n\n\n\u003C!-- \n| Risk Prediction | HeartFailure \u003Cbr> KidneyDisease \u003Cbr> Dementia | LSAN | [LSAN: Modeling Long-term Dependencies and Short-term Correlations with Hierarchical Attention for Risk Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411864) | [Code](https:\u002F\u002Fgithub.com\u002Fdmmlprojs\u002Flsan) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdmmlprojs\u002Flsan?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdmmlprojs\u002Flsan?color=critical&style=social) | CIKM\u003Cbr>2020 -->\n\n\n# [Conferences](#content)\n\n❗ It is highly recommended to utilize [dblp](https:\u002F\u002Fdblp.uni-trier.de\u002F) and [Aminer](https:\u002F\u002Fwww.aminer.cn\u002Fconf) (in Chinese) to search.\n\nSome more useful websites:\n- CCF conference deadlines: https:\u002F\u002Fccfddl.github.io\u002F\n- Conference eye (会议之眼): https:\u002F\u002Fwww.conferenceeye.cn\u002F#\u002Flayout\u002Fhome\n- Call4Papers: http:\u002F\u002F123.57.137.208\u002Fccf\u002Fccf-8.jsp\n- Conference list: http:\u002F\u002Fwww.conferencelist.info\u002Fupcoming.html\n- PMLR: https:\u002F\u002Fproceedings.mlr.press\u002F （contains ICML, AISTATS, ACML, UAI, etc）\n## Table of Conferences\n\n|Conference | Approximate submission time |\n|:--|:--|\n| [IJCAI](#IJCAI) | 1.14\\~2.15 |\n| [ICML](#ICML) | 1.23\\~2.24 |\n| [KDD](#KDD) | 2.3\\~2.17 |\n| [CIKM](#CIKM) | 5.15\\~5.26 |\n| [NeurIPS](#NeurIPS)| 5.18\\~6.5 |\n| [ICDM](#ICDM) | 6.5\\~6.17 |\n| [WSDM](#WSDM) | 7.17\\~8.16 |\n| [AAAI](#AAAI) | 9.5\\~9.15 |\n| [ICLR](#ICLR) | 9.25\\~10.27|\n| [WWW](#WWW) | 10.14\\~11.5|\n| [ICDE-1](#ICDE) | 6.1\\~7.21 |\n| [ICDE-2](#ICDE) | 10.1\\~11.17|\nApproximate conference submission times from the most recent 7 years.\n\n\n## Conference (Journal) CCF Ranks\n\n|Conference (Journal) | CCF Rank |\n|:--|:--|\n| ICML | A |\n| NeurIPS | A | \n| ICLR | None but top |\n| KDD | A | \n| AAAI | A |\n| IJCAI | A | \n| ICDE | A |\n| WWW | A |\n| ACL | A |\n| INFOCOM | A |\n| SIGIR | A |\n| VLDB | A |\n| UbiComp | A |\n| TKDE | A |\n| TPAMI | A |\n| TOIS | A |\n| CIKM | B |\n| ICDM | B |\n| WSDM | B |\n| COLING | B |\n| TNNLS | B |\n| TITS | B |\n| AISTATS | C but top |\n| ICPR | C |\n| Transportation Research Part C | SCI 1 Top |\n\nNote that: AISTATS is CCF C but is top in computational mathematics (such as for probabilistic problems).\n\n## ICML\n\n> Proceeding Page https:\u002F\u002Fproceedings.mlr.press\u002F\n> Homepage https:\u002F\u002Ficml.cc\n\n| Conference | Source | Deadline | Notification |\n| ---------- | ---------------------------------------------------------- | ---------- | ---------- |\n|ICML\u003Cbr>2022|https:\u002F\u002Ficml.cc\u002FConferences\u002F2022\u002FSchedule| Jan 27, 2022 | |\n|ICML\u003Cbr>2021| [https:\u002F\u002Ficml.cc\u002FConferences\u002F2021\u002FSchedule](https:\u002F\u002Ficml.cc\u002FConferences\u002F2021\u002FSchedule)| | |\n| ICML\u003Cbr>2020 | [https:\u002F\u002Ficml.cc\u002FConferences\u002F2020\u002FSchedule](https:\u002F\u002Ficml.cc\u002FConferences\u002F2020\u002FSchedule) | | |\n| ICML\u003Cbr>2019 | [https:\u002F\u002Ficml.cc\u002FConferences\u002F2019\u002FSchedule](https:\u002F\u002Ficml.cc\u002FConferences\u002F2019\u002FSchedule) | | |\n\n## NeurIPS\n\n[All Links](https:\u002F\u002Fpapers.NeurIPS.cc\u002F)\n\n## ICLR\n\nFinding it on openreview:\n\n\n> Homepage https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\n\n| Conference | Source | Deadline | Notification |\n| ---------- | ---------------------------------------------------------- | ---------- | ---------- |\n|ICLR\u003Cbr>2022|https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2022\u002FConference|Oct 06 '21|Jan 24 '22|\n| ICLR\u003Cbr>2021 | [https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2021\u002FConference](https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2021\u002FConference) | | |\n| ICLR\u003Cbr>2020 | [https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2020\u002FConference](https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2020\u002FConference) | | |\n\n## KDD\n\n> Format : https:\u002F\u002Fwww.kdd.org\u002Fkdd20xx\u002Faccepted-papers\n\n| Conference | Source | Deadline | Notification |\n| ---------- | --------------------------------------------------- | ---------- | ---------- |\n|KDD-22|| Feb 10th, 2022 | May 19th, 2022 |\n|KDD-21| [Link](https:\u002F\u002Fkdd.org\u002Fkdd2021\u002Faccepted-papers)| | |\n| KDD-20 | [Link](https:\u002F\u002Fwww.kdd.org\u002Fkdd2020\u002Faccepted-papers) | | |\n| KDD-19 | [Link](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers) | | |\n| KDD-18 | [Link](https:\u002F\u002Fwww.kdd.org\u002Fkdd2018\u002Faccepted-papers) | | |\n| KDD-17 | [Link](https:\u002F\u002Fwww.kdd.org\u002Fkdd2017\u002Faccepted-papers) | | |\n\n\n## AAAI\n\n| Conference | Source | Deadline | Notification |\n| ---------- | ------------------------------------------------------------ | ----------------- | ----------------- |\n|AAAI-22|[Link](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-22\u002Fwp-content\u002Fuploads\u002F2021\u002F12\u002FAAAI-22_Accepted_Paper_List_Main_Technical_Track.pdf)|September 8, 2021|November 29, 2021|\n| AAAI-21 | [Link](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-21\u002Fwp-content\u002Fuploads\u002F2020\u002F12\u002FAAAI-21_Accepted-Paper-List.Main_.Technical.Track_.pdf) | | |\n| AAAI-20 | [Link](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-20\u002Fwp-content\u002Fuploads\u002F2020\u002F01\u002FAAAI-20-Accepted-Paper-List.pdf) | | |\n| AAAI-19 | [Link](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-19\u002Fwp-content\u002Fuploads\u002F2018\u002F11\u002FAAAI-19_Accepted_Papers.pdf) | | |\n| AAAI-18 | [Link](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-18\u002Fwp-content\u002Fuploads\u002F2017\u002F12\u002FAAAI-18-Accepted-Paper-List.Web_.pdf) | | |\n| AAAI-17 | [Link](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2017\u002Faaai17accepted-papers.pdf) | | |\n| AAAI-16 | [Link](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2016\u002Faaai16accepted-papers.pdf) | | |\n| AAAI-15 | [Link](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2015\u002Fiaai15accepted-papers.pdf) | | |\n| AAAI-14 | [Link](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2014\u002Faaai14accepts.php) | | |\n| AAAI-13 | [Link](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2013\u002Faaai13accepts.php) | | |\n\n\n## [IJCAI](https:\u002F\u002Fwww.ijcai.org\u002Fpast_proceedings)\n\n| Conference | Source | Deadline | Notification |\n| ---------- | ----------------------------------------------------------- | ---------- | ---------- |\n|IJCAI-22| [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2022\u002F) | |\n|IJCAI-21|[Link](https:\u002F\u002Fijcai-21.org\u002Fprogram-main-track\u002F)| | |\n| IJCAI-20 | [Link](http:\u002F\u002Fstatic.ijcai.org\u002F2020-accepted_papers.html) | | |\n| IJCAI-19 | [Link](https:\u002F\u002Fwww.ijcai19.org\u002Faccepted-papers.html) | | |\n| IJCAI-18 | [Link](https:\u002F\u002Fwww.ijcai-18.org\u002Faccepted-papers\u002Findex.html) | | |\n| IJCAI-17 | [Link](https:\u002F\u002Fijcai-17.org\u002Faccepted-papers.html) | | |\n| IJCAI-16 | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2016) | | |\n| IJCAI-15 | [Link](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2015) | | |\n| IJCAI-14 | None | | |\n\n\n## ICDE\n\nIEEE International Conference on Data Engineering\n\n[All Links](https:\u002F\u002Fieeexplore.ieee.org\u002Fxpl\u002Fconhome\u002F1000178\u002Fall-proceedings)\n\n## WWW\n\nTheWebConf\n\n| Conference | Source | Deadline | Notification |\n| ---------- | ---------------------------------------------------------- | ---------- | ---------- |\n|WWW-22| [Link](https:\u002F\u002Fwww2022.thewebconf.org\u002Faccepted-papers\u002F)| 2021-10-21 ... | 2022-01-13 ... |\n|WWW-21| [Link](https:\u002F\u002Fwww2021.thewebconf.org\u002Fprogram\u002Fpapers\u002F)| | |\n| WWW-20 | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fproceedings\u002F10.1145\u002F3366423) | | |\n| WWW-19 | [Link](https:\u002F\u002Fwww2019.thewebconf.org\u002Faccepted-papers) | | |\n| WWW-18 | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fproceedings\u002F10.5555\u002F3178876) | | |\n| WWW-17 | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fproceedings\u002F10.1145\u002F3308558) | | |\n\n\n## CIKM\n\nThe Conference on Information and Knowledge Management\n\n[All Links](https:\u002F\u002Fdl.acm.org\u002Fconference\u002Fcikm)\n\n\n## ICDM\n\nIEEE International Conference on Data Mining\n\n[All Links]([https:\u002F\u002Fdl.acm.org\u002Fconference\u002Fcikm](https:\u002F\u002Fieeexplore.ieee.org\u002Fxpl\u002Fconhome\u002F1000179\u002Fall-proceedings))\n\n\n## WSDM\n\nACM Web Search and Data Mining\n\n[All Links](https:\u002F\u002Fdl.acm.org\u002Fconference\u002Fwsdm)\n\n","# 时间序列相关工作与会议\n\n# 待办事项：AAAI2025、ICML2025、AAAI2026、ICLR2026……\n\n\u003C!-- **访问我们的[GitHub页面](https:\u002F\u002Flixus7.github.io\u002FTime-Series-Works-Conferences\u002F)以获得更好的浏览体验。**\n\n\n\u003Ca href=\"#Conferences\">点击此处跳转至会议页面，了解更多会议信息。\u003C\u002Fa>\n\n或访问[AI ML Summary Github](https:\u002F\u002Fgithub.com\u002FLionelsy\u002FConference-Accepted-Paper-List)\n\n一些其他优秀的时间序列相关仓库：\n\n[xiyuanzh\u002Ftime-series-papers](https:\u002F\u002Fgithub.com\u002Fxiyuanzh\u002Ftime-series-papers)\n\n[qingsongedu\u002Fawesome-AI-for-time-series-papers](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)\n\n[xuehaouwa\u002FAwesome-Trajectory-Prediction](https:\u002F\u002Fgithub.com\u002Fxuehaouwa\u002FAwesome-Trajectory-Prediction)\n\n[我的时间序列仓库星级列表](https:\u002F\u002Fgithub.com\u002Fstars\u002Flixus7\u002Flists\u002Ftime-series-list) -->\n\n\u003Cdiv align=\"center\">\n\u003C!-- \u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F54fdbe8888c0a75717d7939b42f3d744b77483b0\u002F687474703a2f2f6a617977636a6c6f76652e6769746875622e696f2f73622f69636f2f617765736f6d652e737667\" \u002F>\n\u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F1ef04f27611ff643eb57eb87cc0f1204d7a6a14d\u002F68747470733a2f2f696d672e736869656c64732e696f2f7374617469632f76313f6c6162656c3d254630253946253843253946266d6573736167653d496625323055736566756c267374796c653d7374796c653d666c617426636f6c6f723d424334453939\" \u002F>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F41e8e16b771d56dd768f7055354613254961d169\u002F687474703a2f2f6a617977636jlove2e6769746875622e696f2f73622f6769746875622f677265656e2d666f6c6f772e737667\" \u002F> \u003C\u002Fa> -->\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Flixus7\u002FTime-Series-Works-Conferences\" \u002F> \u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fnetwork\u002Fmembers\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flixus7\u002FTime-Series-Works-Conferences\" \u002F> \u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fstargazers\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flixus7\u002FTime-Series-Works-Conferences\" \u002F> \u003C\u002Fa>\n\u003C!-- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fblob\u002Fmain\u002Fdocs\u002Fimg\u002FWeChat.jpeg\"> \u003Cimg border=\"0\" src=\"https:\u002F\u002Fcamo.githubusercontent.com\u002F013c283843363c72b1463af208803bfbd5746292\u002F687474703a2f2f6a617977636jlove2e6769746875622e696f2f73622f69636f2f7765636861642e737667\" \u002F> \u003C\u002Fa> -->\n\u003C\u002Fdiv>\n\n\u003C!-- \n\n\n> 我对时间序列研究有着浓厚的兴趣。欢迎与我联系，共同探讨和合作。\n\u003Cbr> 我目前在悉尼新南威尔士大学计算机科学与工程学院攻读博士学位，导师是Flora Salim教授（[Google Scholar](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=Yz35RSYAAAAJ&hl=zh-CN&oi=ao)）和Hao Xue教授（[Google Scholar](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=KwhLl7IAAAAJ&hl=zh-CN&oi=ao)）。此前，我在Xuan Song教授（[Google Scholar](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=_qCSLpMAAAAJ&hl=zh-CN&oi=ao)）、Quanjun Chen教授（[Google Scholar](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=_PKwzTwAAAAJ&hl=zh-CN)）和Renhe Jiang教授（[Google Scholar](https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=Yo2lwasAAAAJ&hl=zh-CN&oi=ao)）的指导下获得了硕士学位。\n\n\n\n任务部分已完成，我们将继续更新方法论部分。如果您发现任何遗漏的资源（论文\u002F代码）或错误，请随时提交问题或拉取请求。此外，如果您有兴趣参与本项目的合作，请随时与我联系。\n\n所有论文均按任务和方法论分类整理，包括未收录于本GitHub仓库中的内容，并可在OneDrive和Google Drive上供所有人使用（需VPN）。 \n\n[OneDrive](https:\u002F\u002F1drv.ms\u002Fu\u002Fs!Au2cJRs-_u93lDbLrSDkDy8htv2V?e=ftuaXd)\n \n[Google Drive](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F17bILWdDxUrufRp3yilYfoU5VKywwS1g6?usp=sharing)\n\n\n\n\n为减少重复，部分数据采用缩写形式。某些术语可能并不代表通用含义，仅适用于本仓库。\n\n|全称 | 缩写|\n|:--|:--|\n| 自适应图神经网络 | AGNN |\n| 注意力 | Attn | \n| 自回归模型（RNN、GRU、LSTM） | AR |\n| 受控微分方程 | CDE | \n| 对比学习 | CL |\n| 编码器-解码器 | EncDec | \n| 集成方法 | Ens |\n| 特征分解 | FeaD |\n| 联邦学习 | FL | \n| 生成对抗网络 | GAN |\n| 图卷积网络 | GCN | \n| 小时、天、周、月等 | HA |\n| 异质图神经网络 | HGNN |\n| 多图神经网络 | MGNN |\n| 记忆 | Mem | \n| 元学习 | MetaL | \n| 多任务学习 | MulT | \n| 网络架构搜索 | NAS | \n| 常微分方程 | ODE |\n| 统计学 | Stat |\n| TCN（WaveNet） | TCN | \n| 时序图网络 | TGN | \n| 变换器 | Trans | \n| 迁移学习 | TransL | \n| 变分自编码器 | VAE | -->\n\n# 最近按任务分类的时间序列相关工作\n\n- \u003Ca href = \"#Multivariat-Time-Series-Forecasting\">多变量时间序列预测\u003C\u002Fa>\n- \u003Ca href = \"#Multivariat-Probabilistic-Time-Series-Forecasting\">多变量概率时间序列预测\u003C\u002Fa>\n- \u003Ca href = \"#Time-Series-Imputation\">时间序列插补\u003C\u002Fa>\n- \u003Ca href = \"#Time-Series-Anomaly-Detection\">时间序列异常检测\u003C\u002Fa>\n- \u003Ca href = \"#Demand-Prediction\">需求预测\u003C\u002Fa>\n- \u003Ca href = \"#Time-Series-Generation\">时间序列生成\u003C\u002Fa>\n- \u003Ca href = \"#Travel-Time-Estimation\">出行时间估计\u003C\u002Fa>\n- \u003Ca href = \"#Traffic-Location-Prediction\">交通位置预测\u003C\u002Fa>\n- \u003Ca href = \"#Event-Prediction\">事件预测\u003C\u002Fa>\n- \u003Ca href = \"#Stock-Prediction\">股票预测\u003C\u002Fa>\n- \u003Ca href = \"#Other-Forecasting\">其他预测\u003C\u002Fa>\n\n# [Multivariat Time Series Forecasting](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| \u003Cimg width=10> | \u003Cimg width=10\u002F> | \u003Cimg width=10\u002F> | \u003Cimg width=100\u002F> | | \u003Cimg width=500\u002F> |\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LightGTS | [LightGTS: A Lightweight General Time Series Forecasting Model](https:\u002F\u002Fopenreview.net\u002Fforum?id=Z5FJsp1U3Z¬eId=5N5JjGUW0m) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FLightGTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FLightGTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FLightGTS?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LETS | [LETS Forecast: Learning Embedology for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=LLk1qYQatJ) | [Code](https:\u002F\u002Fgithub.com\u002Fabrarmajeedi\u002FDeepEDM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fabrarmajeedi\u002FDeepEDM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fabrarmajeedi\u002FDeepEDM?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeBase | [TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=GhTdNOMfOD) | [Code](https:\u002F\u002Fgithub.com\u002Fhqh0728\u002FTimeBase) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhqh0728\u002FTimeBase?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhqh0728\u002FTimeBase?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | RAFT | [Retrieval Augmented Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=GUDnecJdJU) | [Code](https:\u002F\u002Fgithub.com\u002Farchon159\u002FRAFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Farchon159\u002FRAFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Farchon159\u002FRAFT?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CN | [Channel Normalization for Time Series Channel Identification](https:\u002F\u002Fopenreview.net\u002Fforum?id=PqpPrlAQqa) | [Code](https:\u002F\u002Fgithub.com\u002Fseunghan96\u002FCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseunghan96\u002FCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fseunghan96\u002FCN?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeBridge | [TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=pyKO0ZZ5lz) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FTimeBridge) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FTimeBridge?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FTimeBridge?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeStacker | [TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=5RYSqSKz9b) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FTimeBridge) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FTimeBridge?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FTimeBridge?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | WaveToken | [Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization](https:\u002F\u002Fopenreview.net\u002Fforum?id=B6WalMoQJW) | [Code](https:\u002F\u002Fgithub.com\u002Famazon-science\u002Fchronos-forecasting\u002Ftree\u002Fwavetoken) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Moirai-MoE | [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https:\u002F\u002Fopenreview.net\u002Fforum?id=SrEOUSyJcR) | [Code](https:\u002F\u002Fgithub.com\u002FSalesforceAIResearch\u002Funi2ts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSalesforceAIResearch\u002Funi2ts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSalesforceAIResearch\u002Funi2ts?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [In-Context Fine-Tuning for Time-Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=uxzgGLWPj2) | None | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SKOLR | [SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Xg1BGlybfq) | [Code](https:\u002F\u002Fgithub.com\u002Fnetworkslab\u002FSKOLR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnetworkslab\u002FSKOLR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnetworkslab\u002FSKOLR?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | ECL \u003Cbr> Nottingham | FSTLLM | [FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=oyoiHf51es) | [Code](https:\u002F\u002Fgithub.com\u002FJIANGYUE61610306\u002FFSTLLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJIANGYUE61610306\u002FFSTLLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJIANGYUE61610306\u002FFSTLLM?color=critical&style=social) | ICML\u003Cbr>2025\n| Traffic | NYC \u003Cbr> CHI \u003Cbr>SIP \u003Cbr>SD | SynEVO | [SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation](https:\u002F\u002Fopenreview.net\u002Fforum?id=Q3rGQUGgWo) | [Code](https:\u002F\u002Fgithub.com\u002FRodger-Lau\u002FSynEVO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRodger-Lau\u002FSynEVO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRodger-Lau\u002FSynEVO?color=critical&style=social) | ICML\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SEMPO | [SEMPO: Lightweight Foundation Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=YngHXbJM8g) | [Code](https:\u002F\u002Fgithub.com\u002Fmala-lab\u002FSEMPO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmala-lab\u002FSEMPO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmala-lab\u002FSEMPO?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TARFVAE | [TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE](https:\u002F\u002Fopenreview.net\u002Fforum?id=3hnqwOq7iT) | [Code](https:\u002F\u002Fgithub.com\u002FGavine77\u002FTARFVAE) \u003Cbr>! [Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGavine77\u002FTARFVAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGavine77\u002FTARFVAE?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MAFS | [Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation](https:\u002F\u002Fopenreview.net\u002Fforum?id=Uon41HfqR3) | [Code](https:\u002F\u002Fgithub.com\u002Fh505023992\u002FMAFS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fh505023992\u002FMAFS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fh505023992\u002FMAFS?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeXL | [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https:\u002F\u002Fopenreview.net\u002Fforum?id=WRwr2YZ4zt) | None | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DMMV | [Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=PMdHrorFMF) | [Code](https:\u002F\u002Fgithub.com\u002FD2I-Group\u002Fdmmv) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FD2I-Group\u002Fdmmv?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FD2I-Group\u002Fdmmv?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | xLSTM-Mixer | [xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories](https:\u002F\u002Fopenreview.net\u002Fforum?id=JlVn0XRpy0) | [Code](https:\u002F\u002Fgithub.com\u002Fmauricekraus\u002Fxlstm-mixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmauricekraus\u002Fxlstm-mixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmauricekraus\u002Fxlstm-mixer?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TFPS| [Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift](https:\u002F\u002Fopenreview.net\u002Fforum?id=CtoIG9Iwas) | [Code](https:\u002F\u002Fgithub.com\u002FsyrGitHub\u002FTFPS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FsyrGitHub\u002FTFPS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FsyrGitHub\u002FTFPS?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SymTime | [Synthetic Series-Symbol Data Generation for Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=xB1ZNgq0Xp) | [Code](https:\u002F\u002Fgithub.com\u002Fwwhenxuan\u002FSymTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwwhenxuan\u002FSymTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwwhenxuan\u002FSymTime?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | OLinear | [OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain](https:\u002F\u002Fopenreview.net\u002Fforum?id=xB1ZNgq0Xp) | [Code](https:\u002F\u002Fgithub.com\u002Fjackyue1994\u002FOLinear) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjackyue1994\u002FOLinear?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjackyue1994\u002FOLinear?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeEmb | [TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=sLfMvrkn6T) | [Code](https:\u002F\u002Fgithub.com\u002Fshowmeon\u002FTimeEmb) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshowmeon\u002FTimeEmb?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshowmeon\u002FTimeEmb?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-o1 | [Time-o1: Time-Series Forecasting Needs Transformed Label Alignment](https:\u002F\u002Fopenreview.net\u002Fforum?id=RxWILaXuhb) | [Code](https:\u002F\u002Fgithub.com\u002FMaster-PLC\u002FTime-o1) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMaster-PLC\u002FTime-o1?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMaster-PLC\u002FTime-o1?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimePerceiver | [TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=RCeZ063p33) | [Code](https:\u002F\u002Fgithub.comefficient-learning-lab\u002FTimePerceiver) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fefficient-learning-lab\u002FTimePerceiver?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fefficient-learning-lab\u002FTimePerceiver?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MSFT | [Multi-Scale Finetuning for Encoder-based Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=OPOBV0zXu7) | [Code](https:\u002F\u002Fgithub.com\u002Fzqiao11\u002FMSFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzqiao11\u002FMSFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzqiao11\u002FMSFT?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DBLoss | [DBLoss: Decomposition-based Loss Function for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=SbhBIkiRLT) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FDBLoss) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FDBLoss?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FDBLoss?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SRSNet | [Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective](https:\u002F\u002Fopenreview.net\u002Fforum?id=BirE0jYKt0) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FSRSNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FSRSNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FSRSNet?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | IF | [Towards Accurate Time Series Forecasting via Implicit Decoding](https:\u002F\u002Fopenreview.net\u002Fforum?id=gqoeQPhQcE) | [Code](https:\u002F\u002Fgithub.com\u002Frakuyorain\u002FImplicit-Forecaster) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frakuyorain\u002FImplicit-Forecaster?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frakuyorain\u002FImplicit-Forecaster?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat Zero Shot | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TS-RAG | [TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster](https:\u002F\u002Fopenreview.net\u002Fforum?id=PymOnHw4Ty) | [Code](https:\u002F\u002Fgithub.com\u002FUConn-DSIS\u002FTS-RAG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUConn-DSIS\u002FTS-RAG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUConn-DSIS\u002FTS-RAG?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat Traffic| [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | PIR | [Improving Time Series Forecasting via Instance-aware Post-hoc Revision](https:\u002F\u002Fopenreview.net\u002Fforum?id=H7e5RpeIi4) | [Code](https:\u002F\u002Fgithub.com\u002Ficantnamemyself\u002FPIR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ficantnamemyself\u002FPIR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ficantnamemyself\u002FPIR?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat Traffic| Wind \u003Cbr> Temp \u003Cbr> PM25 \u003Cbr> | STELLA | [On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=thHhKPlt8q) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002FSTELLA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002FSTELLA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002FSTELLA?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AliO | [AliO: Output Alignment Matters in Long-Term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=AuOZDp4gy7) | [Code](https:\u002F\u002Fgithub.com\u002Feai-lab\u002FAliO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Feai-lab\u002FAliO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Feai-lab\u002FAliO?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TOTO | [This Time is Different: An Observability Perspective on Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=1jDAYXfcS2) | [Code](https:\u002F\u002Fhuggingface.co\u002FDatadog\u002FToto-Open-Base-1.0) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MoFo| [MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling](https:\u002F\u002Fopenreview.net\u002Fforum?id=sbvLts2HqR) | [Code](https:\u002F\u002Fgithub.com\u002FPoorOtterBob\u002FMoFo) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPoorOtterBob\u002FMoFo?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FPoorOtterBob\u002FMoFo?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning](https:\u002F\u002Fopenreview.net\u002Fforum?id=jy4bBsr1Jc) | [Code](https:\u002F\u002Fgithub.com\u002FSJTU-DMTai\u002FPrune-then-Finetune) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-DMTai\u002FPrune-then-Finetune?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-DMTai\u002FPrune-then-Finetune?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | PIH | [Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Gmwsy7TlFI) | [Code](https:\u002F\u002Fgithub.com\u002Fforever-ly\u002FPIH) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fforever-ly\u002FPIH?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fforever-ly\u002FPIH?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SCAM | [Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=gXOlDLEAjK) | [Code](https:\u002F\u002Fgithub.com\u002FSuDIS-ZJU\u002FSCAM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSuDIS-ZJU\u002FSCAM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSuDIS-ZJU\u002FSCAM?color=critical&style=social) | NIPS\u003Cbr>2025\n| ST SSL | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS07(M) \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | ST-SSDL | [How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=TgGH1bY6kl) | [Code](https:\u002F\u002Fgithub.com\u002FJimmy-7664\u002FST-SSDL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJimmy-7664\u002FST-SSDL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJimmy-7664\u002FST-SSDL?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DecompNet | [DecompNet: Enhancing Time Series Forecasting Models with Implicit Decomposition](https:\u002F\u002Fopenreview.net\u002Fforum?id=ioXn68lBjO) | [Code](https:\u002F\u002Fgithub.com\u002Fluodhhh\u002FDecompNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluodhhh\u002FDecompNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fluodhhh\u002FDecompNet?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr> other | S2TS-LLM | [Bridging Time and Linguistics: LLMs as Time Series Analyzer through Symbolization and Segmentation](https:\u002F\u002Fopenreview.net\u002Fforum?id=nOv6z9RHA5) | [Code](https:\u002F\u002Fgithub.com\u002FJianyangQin\u002FS2TS-LLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJianyangQin\u002FS2TS-LLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJianyangQin\u002FS2TS-LLM?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MSFT | [Multi-Scale Finetuning for Encoder-based Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=OPOBV0zXu7) | [Code](https:\u002F\u002Fgithub.com\u002Fzqiao11\u002FMSFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzqiao11\u002FMSFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzqiao11\u002FMSFT?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AMRC | [Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency](https:\u002F\u002Fopenreview.net\u002Fforum?id=KrglRiOKYT) | [Code](https:\u002F\u002Fgithub.com\u002FMazelTovy\u002FAMRC) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMazelTovy\u002FAMRC?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMazelTovy\u002FAMRC?color=critical&style=social) | NIPS\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SL | [Selective Learning for Deep Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=kgzRy6nD6D) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002Fselective-learning) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002Fselective-learning?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002Fselective-learning?color=critical&style=social) | NIPS\u003Cbr>2025\n| Evolve Traffic | Air-Str\u003Cbr> PEMS-Str \u003Cbr> Energy-Str | EAC | [Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=FRzCIlkM7I) | [Code](https:\u002F\u002Fgithub.com\u002FOnedean\u002FEAC) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FOnedean\u002FEAC?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FOnedean\u002FEAC?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeMixer++ | [TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https:\u002F\u002Fopenreview.net\u002Fforum?id=1CLzLXSFNn) | [Code](https:\u002F\u002Fgithub.com\u002Fkwuking\u002FTimeMixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkwuking\u002FTimeMixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkwuking\u002FTimeMixer?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-MoE | [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https:\u002F\u002Fopenreview.net\u002Fforum?id=e1wDDFmlVu) | [Code](https:\u002F\u002Fgithub.com\u002FTime-MoE\u002FTime-MoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TVNet | [TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation](https:\u002F\u002Fopenreview.net\u002Fforum?id=MZDdTzN6Cy) | [Code](https:\u002F\u002Fgithub.com\u002FTime-MoE\u002FTime-MoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTime-MoE\u002FTime-MoE?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeKAN | [TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=wTLc79YNbh) | [Code](https:\u002F\u002Fgithub.com\u002Fhuangst21\u002FTimeKAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuangst21\u002FTimeKAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuangst21\u002FTimeKAN?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | ICTSP | [In-context Time Series Predictor](https:\u002F\u002Fopenreview.net\u002Fforum?id=dCcY2pyNIO) | [Code](https:\u002F\u002Fgithub.com\u002FLJC-FVNR\u002FIn-context-Time-Series-Predictor) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLJC-FVNR\u002FIn-context-Time-Series-Predictor?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLJC-FVNR\u002FIn-context-Time-Series-Predictor?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FSCA | Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=syC2764fPc) | [Code](https:\u002F\u002Fgithub.com\u002Ftokaka22\u002FICLR25-FSCA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftokaka22\u002FICLR25-FSCA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftokaka22\u002FICLR25-FSCA?color=critical&style=social) | ICLR\u003Cbr>2025\n|Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SimpleTM | SimpleTM: A Simple Baseline for Multivariate Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=oANkBaVci5) | [Code](https:\u002F\u002Fgithub.com\u002Fvsingh-group\u002FSimpleTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvsingh-group\u002FSimpleTM-FSCA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvsingh-group\u002FSimpleTM?color=critical&style=social) | ICLR\u003Cbr>2025\n|Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | Towards Neural Scaling Laws for Time Series Foundation Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=uCqxDfLYrB) | [Code](https:\u002F\u002Fgithub.com\u002FQingrenn\u002FTSFM-ScalingLaws) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FQingrenn\u002FTSFM-ScalingLaws?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FQingrenn\u002FTSFM-ScalingLaws?color=critical&style=social) | ICLR\u003Cbr>2025 \n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Timer-XL | [Timer-XL: Long-Context Transformers for Unified Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=KMCJXjlDDr) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTimer-XL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FTimer-XL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FTimer-XL?color=critical&style=social) | ICLR\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LCESN | [Locally Connected Echo State Networks for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=KeRwLLwZaw) | [Code](https:\u002F\u002Fgithub.com\u002FFloopCZ\u002Fecho-state-networks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFloopCZ\u002Fecho-state-networks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFloopCZ\u002Fecho-state-networks?color=critical&style=social) | ICLR\u003Cbr>2025\n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> ... | AutoSTF | [AutoSTF: Decoupled Neural Architecture Search for Cost-Effective Automated Spatio-Temporal Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709323) | [Code](https:\u002F\u002Fgithub.com\u002Fusail-hkust\u002FAutoSTF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fusail-hkust\u002FAutoSTF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fusail-hkust\u002FAutoSTF?color=critical&style=social) | KDD\u003Cbr>2025\n| Traffic | LargeST | PatchSTG | [Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709177) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FPatchSTG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FPatchSTG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FPatchSTG?color=critical&style=social) | KDD\u003Cbr>2025\n| Traffic | CHITaxi \u003Cbr> CHIBike \u003Cbr> WSHBike \u003Cbr> NYBike | ProST | [ProST: Prompt Future Snapshot on Dynamic Graphs for Spatio-Temporal Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709273) | None | KDD\u003Cbr>2025\n| Traffic \u003Cbr> unseen| NYCTaxi \u003Cbr> NYCBike \u003Cbr> BJTaxi | STEVE | [Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709201) | [Code](https:\u002F\u002Fgithub.com\u002Fbigscity\u002FSTEVE_CODE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbigscity\u002FSTEVE_CODE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbigscity\u002FSTEVE_CODE?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DUET | [DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709325) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FDUET) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FDUET?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FDUET?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TSFM-Bench | [TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737442) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002FTSFM-Bench) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002FTSFM-Bench?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002FTSFM-Bench?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | QuantumTime | [Quantum Time-index Models with Reservoir for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709228) | [Code](https:\u002F\u002Fgithub.com\u002FQuaRobot\u002FQuantumTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FQuaRobot\u002FQuantumTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FQuaRobot\u002FQuantumTime?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | ST-MTM | [ST-MTM: Masked Time Series Modeling with Seasonal-Trend Decomposition for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3690624.3709254) | [Code](https:\u002F\u002Fgithub.com\u002Fhwseo95\u002Fst-mtm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhwseo95\u002Fst-mtm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhwseo95\u002Fst-mtm?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CMA | [CMA: A Unified Contextual Meta-Adaptation Methodology for Time-Series Denoising and Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3711896.3736881) | [Code](https:\u002F\u002Fgithub.com\u002FFancyAI-SCNU\u002FCMA_KDD_2025) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFancyAI-SCNU\u002FCMA_KDD_2025?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFancyAI-SCNU\u002FCMA_KDD_2025?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CrossLinear | [CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736899) | [Code](https:\u002F\u002Fgithub.com\u002Fmumiao2000\u002FCrossLinear) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmumiao2000\u002FCrossLinear?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmumiao2000\u002FCrossLinear?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BLAST | [BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736860) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002FBLAST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002FBLAST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002FBLAST?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeCapsule | [TimeCapsule: Solving the Jigsaw Puzzle of Long-Term Time Series Forecasting with Compressed Predictive Representations](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737157) | [Code](https:\u002F\u002Fgithub.com\u002FLuoauoa\u002FTimeCapsule) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLuoauoa\u002FTimeCapsule?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLuoauoa\u002FTimeCapsule?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MoA | [Semantics-Aware Patch Encoding and Hierarchical Dependency Modeling for Long-Term Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737123) | [Code](https:\u002F\u002Fgithub.com\u002Flunaaa95\u002Fmou) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flunaaa95\u002Fmou?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flunaaa95\u002Fmou?color=critical&style=social) | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SDE | [SDE: A Simplified and Disentangled Dependency Encoding Framework for State Space Models in Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3737119) | [Code](https:\u002F\u002Fgithub.com\u002FYukinoAsuna\u002FSAMBA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYukinoAsuna\u002FSAMBA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYukinoAsuna\u002FSAMBA?color=critical&style=social) | KDD\u003Cbr>2025\n| Traffic | BIKE \u003Cbr> PEMS03 \u003Cbr> BJ500 \u003Cbr> METR-LA | STH-SepNet | [Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736904) | [Code](https:\u002F\u002Fgithub.com\u002Fjiawenchen10\u002FSTHSepNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjiawenchen10\u002FSTHSepNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjiawenchen10\u002FSTHSepNet?color=critical&style=social) | KDD\u003Cbr>2025\n| Evolve Traffic | Electricity \u003Cbr> PeMS \u003Cbr> Weather | STEV | [Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3711896.3736854) | None | KDD\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SoP | [Non-collective Calibrating Strategy for Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2025\u002F0371) | [Code](https:\u002F\u002Fgithub.com\u002Fhanyuki23\u002FSoP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhanyuki23\u002FSoP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhanyuki23\u002FSoP?color=critical&style=social) | IJCAI\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | VisMoE | [Seeing Sequences like Humans: Pattern Classification Driven Time-Series Forecasting via Vision Language Models](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761199) | [Code](https:\u002F\u002Fgithub.com\u002FLiu905169\u002FVisMoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiu905169\u002FVisMoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiu905169\u002FVisMoE?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BIM3 | [Bidirectional Temporal-Aware Modeling with Multi-Scale Mixture-of-Experts for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761273) | [Code](https:\u002F\u002Fgithub.com\u002Fyifan-gao-dev\u002FBIM3) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyifan-gao-dev\u002FBIM3?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyifan-gao-dev\u002FBIM3?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BALM-TS | [BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761278) | [Code](https:\u002F\u002Fgithub.com\u002FShiqiaoZhou\u002FBALM-TSF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FShiqiaoZhou\u002FBALM-TSF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FShiqiaoZhou\u002FBALM-TSF?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AdaPatch | [AdaPatch: Adaptive Patch-Level Modeling for Non-Stationary Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761360) | [Code](https:\u002F\u002Fgithub.com\u002Fiuaku\u002FAdaPatch) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fiuaku\u002FAdaPatch?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fiuaku\u002FAdaPatch?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | WDformer | [WDformer: A Wavelet-based Differential Transformer Model for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761348) | [Code](https:\u002F\u002Fgithub.com\u002Fxiaowangbc\u002FWDformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxiaowangbc\u002FWDformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxiaowangbc\u002FWDformer?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | HRCformer | [HRCformer: Hierarchical Recursive Convolution-Transformer with Multi-Scale Adaptive Recalibration for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761308) | None | CIKM\u003Cbr>2025\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> China-AQI \u003Cbr> Electricity \u003Cbr> Solar \u003Cbr> Temperature | ST-Hyper | [ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761281) | None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | EAPformer | [Bidirectional Temporal-Aware Modeling with Multi-Scale Mixture-of-Experts for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761055) | [Code](https:\u002F\u002Fgithub.com\u002FIvER1234689\u002FMultivariate-Long-Term-Time-Series-Forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FIvER1234689\u002FMultivariate-Long-Term-Time-Series-Forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FIvER1234689\u002FMultivariate-Long-Term-Time-Series-Forecasting?color=critical&style=social) | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MillGNN | [MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761173) | None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MSOFormer | [MSOFormer: Multi-scale Transformer with Orthogonal Embedding and Frequency Modeling for Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761143) | None | CIKM\u003Cbr>2025\n| Zero Shot | Parking \u003Cbr> [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DANet | [DANet: A RAG-inspired Dual Attention Model for Few-shot Time Series Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761012) | None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Structural Entropy-based Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761007) | None| CIKM\u003Cbr>2025\n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | TopKNet | [TopKNet:Learning to Perceive the Top-K Pivotal Nodes in Spatio-Temporal Data for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3760993) | [Code](https:\u002F\u002Fgithub.com\u002Frandomforest1111\u002FTopKNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frandomforest1111\u002FTopKNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frandomforest1111\u002FTopKNet?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | NYCTaxi \u003Cbr> CityBike \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | ST-LINK | [ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761085) | [Code](https:\u002F\u002Fgithub.com\u002FHyoTaek98\u002FST_LINK) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHyoTaek98\u002FST_LINK?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHyoTaek98\u002FST_LINK?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic \u003Cbr> Random Missing | PEMS04 \u003Cbr> PEMS08 | STMMoE | [Spatio-Temporal Forecasting under Open-World Missingness with Adaptive Mixture-of-Experts](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761403) | [Code](https:\u002F\u002Fgithub.com\u002Fchenywu\u002FSTMMoE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenywu\u002FSTMMoE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenywu\u002FSTMMoE?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic \u003Cbr> Node Missing | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> ... | STA-GANN | [STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761045) | [Code](https:\u002F\u002Fgithub.com\u002Fblisky-li\u002FSTAGANN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fblisky-li\u002FSTAGANN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fblisky-li\u002FSTAGANN?color=critical&style=social) | CIKM\u003Cbr>2025\n| Finance | Crypto \u003Cbr> Forex \u003Cbr> Future\u003Cbr> Stock\u003Cbr> Econ\u003Cbr> Others | FinCast | [FinCast: A Foundation Model for Financial Time-Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761261) | [Code](https:\u002F\u002Fgithub.com\u002Fvincent05r\u002FFinCast-fts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvincent05r\u002FFinCast-fts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvincent05r\u002FFinCast-fts?color=critical&style=social) | CIKM\u003Cbr>2025\n| Wind Power | China \u003Cbr> Texas | | [Multivariate Wind Power Time Series Forecasting with Noise-Filtering Neural ODEs](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761118) | None| CIKM\u003Cbr>2025\n| Traffic | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> CHIBike | DSformer | [Extracting Global Temporal Patterns Within Short Look-Back Windows for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761212) | [Code](https:\u002F\u002Fgithub.com\u002Fsky836\u002FDSFormer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsky836\u002FDSFormer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsky836\u002FDSFormer?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DoP | [Decoder-only Pre-training Enhancement for Spatio-temporal Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761432) | [Code](https:\u002F\u002Fgithub.com\u002Fhikvision-research\u002FDoP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhikvision-research\u002FDoP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhikvision-research\u002FDoP?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | PEMS07(M) \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> NYCTaxi \u003Cbr> NYCBike | SSMOE | [Mixture of Semantic and Spatial Experts for Explainable Traffic Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761412) | None | CIKM\u003Cbr>2025\n| Traffic | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | MultiGran | [Forecasting at Full Spectrum: Holistic Multi-Granular Traffic Modeling under High-Throughput Inference Regimes](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761330) | None | CIKM\u003Cbr>2025\n| Traffic | I-80 \u003Cbr> US-101 \u003Cbr> Complex-\u003Cbr>highway | TPN | [Balance and Brighten: A Twin-Propeller Network to Release Potential of Physics Laws for Traffic State Estimation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761207) | [Code](https:\u002F\u002Fgithub.com\u002Fxxxabc01\u002FTPN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxxxabc01\u002FTPN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxxxabc01\u002FTPN?color=critical&style=social) | CIKM\u003Cbr>2025\n| Traffic | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr>Jinan | FEDDGCN | [FEDDGCN: A Frequency-Enhanced Decoupling Dynamic Graph Convolutional Network for Traffic Flow Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3746252.3761048) |None | CIKM\u003Cbr>2025\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SSCNN | [Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2024\u002Fhash\u002F7b122d0a0dcb1a86ffa25ccba154652b-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FSSCNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJLDeng\u002FSSCNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJLDeng\u002FSSCNN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Are Language Models Actually Useful for Time Series Forecasting?](https:\u002F\u002Fopenreview.net\u002Fforum?id=54NSHO0lFe) | [Code](https:\u002F\u002Fgithub.com\u002FBennyTMT\u002FLLMsForTimeSeries) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBennyTMT\u002FLLMsForTimeSeries?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBennyTMT\u002FLLMsForTimeSeries?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | PGN | [PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=ypEamFKu2O¬eId=jpzTU4OIxe) | [Code](https:\u002F\u002Fgithub.com\u002FWater2sea\u002FTPGN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWater2sea\u002FTPGN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWater2sea\u002FTPGN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CATS | [Are Self-Attentions Effective for Time Series Forecasting?](https:\u002F\u002Fopenreview.net\u002Fforum?id=iN43sJoib7¬eId=VrwF0T4VGH) | [Code](https:\u002F\u002Fgithub.com\u002Fdongbeank\u002FCATS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdongbeank\u002FCATS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdongbeank\u002FCATS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Attraos | [Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective](https:\u002F\u002Fopenreview.net\u002Fforum?id=fEYHZzN7kX) | [Code](https:\u002F\u002Fgithub.com\u002FCityMind-Lab\u002FNeurIPS24-Attraos) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCityMind-Lab\u002FNeurIPS24-Attraos?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCityMind-Lab\u002FNeurIPS24-Attraos?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-FFM | [Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=HS0faHRhWD) | [Code](https:\u002F\u002Fgithub.com\u002Fyuppielqx\u002FTime-FFM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuppielqx\u002FTime-FFM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuppielqx\u002FTime-FFM?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Chimera | [Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=ncYGjx2vnE) | [Code](https:\u002F\u002Fgithub.com\u002FABehrouz\u002FChimera) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FABehrouz\u002FChimera?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FABehrouz\u002FChimera?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TimeXer | [TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables](https:\u002F\u002Fopenreview.net\u002Fforum?id=INAeUQ04lT) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTimeXer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FTimeXer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FTimeXer?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | MiTSformer| [Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment](https:\u002F\u002Fopenreview.net\u002Fforum?id=EMV8nIDZJn) | [Code](https:\u002F\u002Fgithub.com\u002Fchunhuiz\u002FMiTSformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchunhuiz\u002FMiTSformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchunhuiz\u002FMiTSformer?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TTMs| [Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero\u002FFew-Shot Forecasting of Multivariate Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=3O5YCEWETq) | [Code](https:\u002F\u002Fgithub.com\u002Fibm-granite\u002Fgranite-tsfm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fibm-granite\u002Fgranite-tsfm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fibm-granite\u002Fgranite-tsfm?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Sumba| [Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics](https:\u002F\u002Fopenreview.net\u002Fforum?id=co7DsOwcop) | [Code](https:\u002F\u002Fgithub.com\u002Fchenxiaodanhit\u002FSumba) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenxiaodanhit\u002FSumba?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenxiaodanhit\u002FSumba?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Peri-midF | [Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis](https:\u002F\u002Fopenreview.net\u002Fforum?id=5iUxMVJVEV) | [Code](https:\u002F\u002Fgithub.com\u002FWuQiangXDU\u002FPeri-midFormer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWuQiangXDU\u002FPeri-midFormer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWuQiangXDU\u002FPeri-midFormer?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Ada-MSHyper | [Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=RNbrIQ0se8) | [Code](https:\u002F\u002Fgithub.com\u002Fshangzongjiang\u002FAda-MSHyper) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshangzongjiang\u002FAda-MSHyper?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshangzongjiang\u002FAda-MSHyper?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | ... | LPTM | [Large Pre-trained time series models for cross-domain Time series analysis tasks](https:\u002F\u002Fopenreview.net\u002Fforum?id=vMMzjCr5Zj) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FLPTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FLPTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FLPTM?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CCM | [From Similarity to Superiority: Channel Clustering for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=MDgn9aazo0) | [Code](https:\u002F\u002Fgithub.com\u002FGraph-and-Geometric-Learning\u002FTimeSeriesCCM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-and-Geometric-Learning\u002FTimeSeriesCCM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-and-Geometric-Learning\u002FTimeSeriesCCM?color=critical&style=social) | NIPS\u003Cbr>2024\n| Add News | Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Bitcoin | | [From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection](https:\u002F\u002Fopenreview.net\u002Fforum?id=DpByqSbdhI) | [Code](https:\u002F\u002Fgithub.com\u002Fameliawong1996\u002FFrom_News_to_Forecast) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fameliawong1996\u002FFrom_News_to_Forecast?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fameliawong1996\u002FFrom_News_to_Forecast?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | ImageBind \u003Cbr> IMU2CLIP \u003Cbr> IMUGPT \u003Cbr> HARGPT \u003Cbr> LLaVA | UniMTS | [UniMTS: Unified Pre-training for Motion Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=DpByqSbdhI) | [Code](https:\u002F\u002Fgithub.com\u002Fxiyuanzh\u002FUniMTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxiyuanzh\u002FUniMTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxiyuanzh\u002FUniMTS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Attack | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> Weather \u003Cbr> ETTm1 | BackTime | [BackTime: Backdoor Attacks on Multivariate Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=y8HUXkwAOg) | [Code](https:\u002F\u002Fgithub.com\u002Fxiaolin-cs\u002FBackTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxiaolin-cs\u002FBackTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxiaolin-cs\u002FBackTime?color=critical&style=social) | NIPS\u003Cbr>2024\n| Less data | Electricity \u003Cbr> Solar \u003Cbr> Traffic \u003Cbr> PEMS-BAY \u003Cbr> METR-LA | ChronoEpilogi | [ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions](https:\u002F\u002Fopenreview.net\u002Fforum?id=y8HUXkwAOg) | [Code](https:\u002F\u002Fgithub.com\u002Fev07\u002FChronoEpilogi) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fev07\u002FChronoEpilogi?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fev07\u002FChronoEpilogi?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FAN | [Frequency Adaptive Normalization For Non-stationary Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=T0axIflVDD) | [Code](https:\u002F\u002Fgithub.com\u002Fwayne155\u002FFAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwayne155\u002FFAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwayne155\u002FFAN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | GLAFF | [Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective](https:\u002F\u002Fopenreview.net\u002Fforum?id=EY2agT920S) | [Code](https:\u002F\u002Fgithub.com\u002FForestsKing\u002FGLAFF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FForestsKing\u002FGLAFF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FForestsKing\u002FGLAFF?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FilterNet | [FilterNet: Harnessing Frequency Filters for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=ugL2D9idAD) | [Code](https:\u002F\u002Fgithub.com\u002Faikunyi\u002FFilterNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faikunyi\u002FFilterNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faikunyi\u002FFilterNet?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CycleNet | [CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns](https:\u002F\u002Fopenreview.net\u002Fforum?id=clBiQUgj4w) | [Code](https:\u002F\u002Fgithub.com\u002FACAT-SCUT\u002FCycleNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FACAT-SCUT\u002FCycleNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FACAT-SCUT\u002FCycleNet?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | RATD | [Retrieval-Augmented Diffusion Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=dRJJt0Ji48¬eId=8wGyyvVUNr) | [Code](https:\u002F\u002Fgithub.com\u002Fstanliu96\u002FRATD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fstanliu96\u002FRATD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fstanliu96\u002FRATD?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DDN | [DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=RVZfra6sZo) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FDDN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FDDN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FDDN?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FBM | [Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=BAfKBkr8IP) | [Code](https:\u002F\u002Fgithub.com\u002Frunze1223\u002FFourier-Basis-Mapping) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frunze1223\u002FFourier-Basis-Mapping?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frunze1223\u002FFourier-Basis-Mapping?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | BSA | [Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=dxyNVEBQMp) | [Code](https:\u002F\u002Fgithub.com\u002FDJLee1208\u002FBSA_2024) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDJLee1208\u002FBSA_2024?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDJLee1208\u002FBSA_2024?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DeformableTST | [DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching](https:\u002F\u002Fopenreview.net\u002Fforum?id=B1Iq1EOiVU) | [Code](https:\u002F\u002Fgithub.com\u002Fluodhhh\u002FDeformableTST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluodhhh\u002FDeformableTST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fluodhhh\u002FDeformableTST?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SOFTS | [SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion](https:\u002F\u002Fopenreview.net\u002Fforum?id=89AUi5L1uA) | [Code](https:\u002F\u002Fgithub.com\u002FSecilia-Cxy\u002FSOFTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSecilia-Cxy\u002FSOFTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSecilia-Cxy\u002FSOFTS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | | [Scaling Law for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Cr2jEHJB9q) | [Code](https:\u002F\u002Fgithub.com\u002FJingzheShi\u002FScalingLawForTimeSeriesForecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJingzheShi\u002FScalingLawForTimeSeriesForecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJingzheShi\u002FScalingLawForTimeSeriesForecasting?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | AutoTimes | [AutoTimes: Autoregressive Time Series Forecasters via Large Language Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=HS0faHRhWD) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FAutoTimes) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FAutoTimes?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FAutoTimes?color=critical&style=social) | NIPS\u003Cbr>2024\n| Multi Task | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | UniTS | [UniTS: A Unified Multi-Task Time Series Model](https:\u002F\u002Fopenreview.net\u002Fforum?id=nBOdYBptWW) | [Code](https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FUniTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmims-harvard\u002FUniTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmims-harvard\u002FUniTS?color=critical&style=social) | NIPS\u003Cbr>2024\n| Foundation TS | ... | MOMENT | [MOMENT: A Family of Open Time-series Foundation Models](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F34530) | [Code](https:\u002F\u002Fgithub.com\u002Fmoment-timeseries-foundation-model\u002Fmoment) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmoment-timeseries-foundation-model\u002Fmoment?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmoment-timeseries-foundation-model\u002Fmoment?color=critical&style=social) | ICML\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | OSL | [An Analysis of Linear Time Series Forecasting Models](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F32697) | [Code](https:\u002F\u002Fgithub.com\u002Fsir-lab\u002Flinear-forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsir-lab\u002Flinear-forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsir-lab\u002Flinear-forecasting?color=critical&style=social) | ICML\u003Cbr>2024\n| Six | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | UP2ME | [UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F33686) | [Code](https:\u002F\u002Fgithub.com\u002FThinklab-SJTU\u002FUP2ME) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FThinklab-SJTU\u002FUP2ME?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FThinklab-SJTU\u002FUP2ME?color=critical&style=social) | ICML\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SparseTSF | [SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters](https:\u002F\u002Fopenreview.net\u002Fforum?id=54NSHO0lFe) | [Code](https:\u002F\u002Fgithub.com\u002Flss-1138\u002FSparseTSF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flss-1138\u002FSparseTSF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flss-1138\u002FSparseTSF?color=critical&style=social) | ICML\u003Cbr>2024\n| Multivariat | Electricity \u003Cbr> PEMSD7M \u003Cbr> BikeNYC \u003Cbr> [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SCNN | [Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10457027) | [Code](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FSCNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJLDeng\u002FSCNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJLDeng\u002FSCNN?color=critical&style=social) | TKDE \u003Cbr> 2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | iTransformer | [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=JePfAI8fah) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FiTransformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FiTransformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FiTransformer?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | NorPool \u003Cbr> Caiso \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Exchange \u003Cbr> ETT \u003Cbr> Wind | mr-Diff | [Multi-Resolution Diffusion Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=mmjnr0G8ZY) | None | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Traffic \u003Cbr> Exchange \u003Cbr> ILI | ModernTCN | [Multi-Resolution Diffusion Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU) | [Code](https:\u002F\u002Fgithub.com\u002Fluodhhh\u002FModernTCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluodhhh\u002FModernTCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fluodhhh\u002FModernTCN?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Time-LLM | [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https:\u002F\u002Fopenreview.net\u002Fforum?id=Unb5CVPtae) | [Code](https:\u002F\u002Fgithub.com\u002FKimMeen\u002FTime-LLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKimMeen\u002FTime-LLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKimMeen\u002FTime-LLM?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | TEMPO | [TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=YH5w12OUuU) | [Code](https:\u002F\u002Fgithub.com\u002FDC-research\u002FTEMPO) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDC-research\u002FTEMPO?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDC-research\u002FTEMPO?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CARD | [CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=MJksrOhurE) | [Code](https:\u002F\u002Fgithub.com\u002Fwxie9\u002FCARD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwxie9\u002FCARD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwxie9\u002FCARD?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | ARM | [ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=JWpwDdVbaM) | None | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DAM | [DAM: Towards a Foundation Model for Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=4NhMhElWqP) | [None](https:\u002F\u002Fopenreview.net\u002Fattachment?id=4NhMhElWqP&name=supplementary_material) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr> PEMS3478 | TimeMixer | [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=7oLshfEIC2) | [Code](https:\u002F\u002Fgithub.com\u002Fkwuking\u002FTimeMixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkwuking\u002FTimeMixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkwuking\u002FTimeMixer?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | PDF | [Periodicity Decoupling Framework for Long-term Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=dp27P5HBBt) | [Code](https:\u002F\u002Fgithub.com\u002FHank0626\u002FPDF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHank0626\u002FPDF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHank0626\u002FPDF?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat \u003Cbr> Missing Value| METR-LA \u003Cbr> Electricity \u003Cbr> PEMS \u003Cbr> ETT \u003Cbr> BeijingAir| BiTGraph | [Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values](https:\u002F\u002Fopenreview.net\u002Fforum?id=O9nZCwdGcG) | [Code](https:\u002F\u002Fgithub.com\u002Fchenxiaodanhit\u002FBiTGraph) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenxiaodanhit\u002FBiTGraph?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenxiaodanhit\u002FBiTGraph?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr> PEMS08 | LIFT | [Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators](https:\u002F\u002Fopenreview.net\u002Fforum?id=JiTVtCUOpS) | [Code](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FLIFT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FLIFT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FLIFT?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Traffic | STanHop | [STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=6iwg437CZs) | [Code](https:\u002F\u002Fgithub.com\u002FMAGICS-LAB\u002FSTanHop) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMAGICS-LAB\u002FSTanHop?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMAGICS-LAB\u002FSTanHop?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> ILI \u003Cbr> CloudCluster | Pathformer | [Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU) | [Code](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002Fpathformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdecisionintelligence\u002Fpathformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdecisionintelligence\u002Fpathformer?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | pits | [Learning to Embed Time Series Patches Independently](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU) | [Code](https:\u002F\u002Fgithub.com\u002Fseunghan96\u002Fpits) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseunghan96\u002Fpits?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fseunghan96\u002Fpits?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic | FITS | [FITS: Modeling Time Series with 10k Parameters](https:\u002F\u002Fopenreview.net\u002Fforum?id=bWcnvZ3qMb) | [Code](https:\u002F\u002Fgithub.com\u002FVEWOXIC\u002FFITS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVEWOXIC\u002FFITS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVEWOXIC\u002FFITS?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Lora | AutoTCL | [Parametric Augmentation for Time Series Contrastive Learnin](https:\u002F\u002Fopenreview.net\u002Fforum?id=EIPLdFy3vp) | [Code](https:\u002F\u002Fgithub.com\u002FAslanDing\u002FAutoTCL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAslanDing\u002FAutoTCL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAslanDing\u002FAutoTCL?color=critical&style=social) | ICLR\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Exchange \u003Cbr> ILI | GLIP | [Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=aFWUY3E7ws) | [Code](https:\u002F\u002Fopenreview.net\u002Fattachment?id=aFWUY3E7ws&name=supplementary_material) | ICLR\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Fredformer | [Fredformer: Frequency Debiased Transformer for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671855) | [Code](https:\u002F\u002Fgithub.com\u002FchenzRG\u002FFredformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FchenzRG\u002FFredformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FchenzRG\u002FFredformer?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | GPHT | [Generative Pretrained Hierarchical Transformer for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671855) | [Code](https:\u002F\u002Fgithub.com\u002Ficantnamemyself\u002FGPHT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ficantnamemyself\u002FGPHT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ficantnamemyself\u002FGPHT?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | FRNet | [FRNet: Frequency-based Rotation Network for Long-term Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671713) | [Code](https:\u002F\u002Fgithub.com\u002FSiriZhang45\u002FFRNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSiriZhang45\u002FFRNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSiriZhang45\u002FFRNet?color=critical&style=social) | KDD\u003Cbr>2024\n| Missing \u003Cbr> MTS | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> China AQI | GinAR | [GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3672055) | [Code](https:\u002F\u002Fgithub.com\u002FGestaltCogTeam\u002FGinAR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGestaltCogTeam\u002FGinAR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGestaltCogTeam\u002FGinAR?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | HimNet | [Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671961) | [Code](https:\u002F\u002Fgithub.com\u002FXDZhelheim\u002FHimNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FXDZhelheim\u002FHimNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FXDZhelheim\u002FHimNet?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CDS | [Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671926) | [Code](https:\u002F\u002Fgithub.com\u002FHALF111\u002Fcalibration_CDS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHALF111\u002Fcalibration_CDS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHALF111\u002Fcalibration_CDS?color=critical&style=social) | KDD\u003Cbr>2024\n| Foundation \u003Cbr> Traffic | TaxiBJ \u003Cbr> Crawd \u003Cbr> BikeNYC \u003Cbr> Cellular \u003Cbr> TDrive \u003Cbr> TrafficSH | UniST | [UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671662) | [Code](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FUniST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FUniST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FUniST?color=critical&style=social) | KDD\u003Cbr>2024\n| Early \u003Cbr> Traffic | METR-LA \u003Cbr> EMS \u003Cbr> NYPD | STEMO | [STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671922) | [Code](https:\u002F\u002Fgithub.com\u002Fcoco0106\u002FMO-STEP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcoco0106\u002FMO-STEP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcoco0106\u002FMO-STEP?color=critical&style=social) | KDD\u003Cbr>2024\n| New nodes \u003Cbr> Traffic | Large-ST | STONE | [STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671680) | [Code](https:\u002F\u002Fgithub.com\u002FPoorOtterBob\u002FSTONE-KDD-2024) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPoorOtterBob\u002FSTONE-KDD-2024?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FPoorOtterBob\u002FSTONE-KDD-2024?color=critical&style=social) | KDD\u003Cbr>2024\n| Irregular \u003Cbr> Traffic | Zhuzhou \u003Cbr> Baoding | Aseer | [Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671665) | [Code](https:\u002F\u002Fgithub.com\u002Fusail-hkust\u002FASeer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fusail-hkust\u002FASeer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fusail-hkust\u002FASeer?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | Stock \u003Cbr> Exchange \u003Cbr> Weather | CONTIME | [Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671969) | [Code](https:\u002F\u002Fgithub.com\u002Fsheoyon-jhin\u002FCONTIME) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsheoyon-jhin\u002FCONTIME?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsheoyon-jhin\u002FCONTIME?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | PEMS07 \u003Cbr> Large-ST | GWT | [Pre-Training Identification of Graph Winning Tickets in Adaptive Spatial-Temporal Graph Neural Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671912) | [Code](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002Fpaper-1430) | KDD\u003Cbr>2024\n| Large Scale | Large-ST | RPMixer | [RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671881) | [Code](https:\u002F\u002Fsites.google.com\u002Fview\u002Frpmixer) | KDD\u003Cbr>2024\n| Demand Supply \u003Cbr> Prediction | Shanghai \u003Cbr> Zhengzhou | MulSTE | [MulSTE: A Multi-view Spatio-temporal Learning Framework with Heterogeneous Event Fusion for Demand-supply Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3672030) | [Code](https:\u002F\u002Fgithub.com\u002Fmulste-kdd2024\u002FMulSTE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmulste-kdd2024\u002FMulSTE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmulste-kdd2024\u002FMulSTE?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | 108s | AutoXPCR | [AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3672057) | [TF](https:\u002F\u002Fgithub.com\u002Fraphischer\u002Fxpcr) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fraphischer\u002Fxpcr?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fraphischer\u002Fxpcr?color=critical&style=social) | KDD\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | UniTime | [UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3589334.3645434) | [Code](https:\u002F\u002Fgithub.com\u002Fliuxu77\u002FUniTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliuxu77\u002FUniTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliuxu77\u002FUniTime?color=critical&style=social) | WWW 2024\n| Multivariat | Ross \u003Cbr> Saratoga \u003Cbr> UpperPen \u003Cbr> SFC | DAN | [Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F27768) | [Code](https:\u002F\u002Fgithub.com\u002Fdavidanastasiu\u002Fdan) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdavidanastasiu\u002Fdan?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdavidanastasiu\u002Fdan?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | ILI \u003Cbr> Weather \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> ETT \u003Cbr> Exchange | HDMixer | [HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29155) | [Code](https:\u002F\u002Fgithub.com\u002Fhqh0728\u002FHDMixer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhqh0728\u002FHDMixer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhqh0728\u002FHDMixer?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> England \u003Cbr> TaxiBJ \u003Cbr> PEMS-BAY | STPGNN | [Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28707) | None | AAAI\u003Cbr>2024\n| Multivariat | FD001 \u003Cbr> FD002 \u003Cbr> FD003 \u003Cbr> FD004 | FC-STGNN | [Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29500) | [Code](https:\u002F\u002Fgithub.com\u002FFrank-Wang-oss\u002FFCSTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFrank-Wang-oss\u002FFCSTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFrank-Wang-oss\u002FFCSTGNN?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | PEMS04 \u003Cbr> PEMS08 \u003Cbr> blockchain | TMP-Nets | [Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29051) | None | AAAI\u003Cbr>2024\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY | ModWaveMLP | [ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28753) | [TF](https:\u002F\u002Fgithub.com\u002FKqingzheng\u002FModWaveMLP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKqingzheng\u002FModWaveMLP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKqingzheng\u002FModWaveMLP?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat |Flight \u003Cbr> Weather \u003Cbr> ETT \u003Cbr> Electricity \u003Cbr> Exchange | MSGNet | [MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28991) | [Code](https:\u002F\u002Fgithub.com\u002FYoZhibo\u002FMSGNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYoZhibo\u002FMSGNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYoZhibo\u002FMSGNet?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat | Self-PeMS | DLF | [Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28759) | [Code](https:\u002F\u002Fgithub.com\u002Fwangbinwu13116175205\u002FDLF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwangbinwu13116175205\u002FDLF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwangbinwu13116175205\u002FDLF?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat |ETT \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Exchange | HTV-Trans | [Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29483) | [Code](https:\u002F\u002Fgithub.com\u002Fflare200020\u002FHTV_Trans) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fflare200020\u002FHTV_Trans?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fflare200020\u002FHTV_Trans?color=critical&style=social) | AAAI\u003Cbr>2024\n| Multivariat |A-share \u003Cbr> Cross-Market \u003Cbr> ETT | ST-DAN| [Adaptive Meta-Learning Probabilistic Inference Framework for Long Sequence Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29661) | [Code](https:\u002F\u002Fgithub.com\u002FZhu-JP\u002FAMPIF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhu-JP\u002FAMPIF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZhu-JP\u002FAMPIF?color=critical&style=social) | AAAI\u003Cbr>2024\n| Six | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | CTRL | [An NCDE-based Framework for Universal Representation Learning of Time Series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F511) | [Code](https:\u002F\u002Fgithub.com\u002FLiuZH-19\u002FCTRL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiuZH-19\u002FCTRL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiuZH-19\u002FCTRL?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic | PEMS3478 | STD-MAE | [Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F442) | [Code](https:\u002F\u002Fgithub.com\u002FJimmy-7664\u002FSTD-MAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJimmy-7664\u002FSTD-MAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJimmy-7664\u002FSTD-MAE?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | DERITS | [Deep Frequency Derivative Learning for Non-stationary Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F436) | None | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | Skip-Timef | [Skip-Timeformer: Skip-Time Interaction Transformer for Long Sequence Time-Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F608) | None | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | VCformer | [VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F590) | [Code](https:\u002F\u002Fgithub.com\u002FCSyyn\u002FVCformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCSyyn\u002FVCformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCSyyn\u002FVCformer?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | LeRet | [LeRet: Language-Empowered Retentive Network for Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F460) | [Code](https:\u002F\u002Fgithub.com\u002Fhqh0728\u002FLeRet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhqh0728\u002FLeRet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhqh0728\u002FLeRet?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Missing Variate | METR-LA \u003Cbr> Solar \u003Cbr> Traffic \u003Cbr> ECG5000 | SDformer | [SDformer: Transformer with Spectral Filter and Dynamic Attention for Multivariate Time Series Long-term Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F228) | None | IJCAI\u003Cbr>2024\n| Traffic | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMSD7M | DCST | [Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F288) | [Code](https:\u002F\u002Fgithub.com\u002Fibizatomorrow\u002FDCST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fibizatomorrow\u002FDCST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fibizatomorrow\u002FDCST?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic | METR-LA \u003Cbr> PEMS-BAY | ST-nFBST | [Full Bayesian Significance Testing for Neural Networks in Traffic Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F245) | [Code](https:\u002F\u002Fgithub.com\u002Fliuzh-buaa\u002FST-nFBST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliuzh-buaa\u002FST-nFBST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliuzh-buaa\u002FST-nFBST?color=critical&style=social) | IJCAI\u003Cbr>2024\n| multi-source \u003Cbr> SSL | BikeIn \u003Cbr> BikeOut \u003Cbr> TaxiIn \u003Cbr> TaxiOut \u003Cbr> Air | MoSSL | [Multi-Modality Spatio-Temporal Forecasting via Self-Supervised Learning](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F223) | [Code](https:\u002F\u002Fgithub.com\u002Fbeginner-sketch\u002FMoSSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbeginner-sketch\u002FMoSSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbeginner-sketch\u002FMoSSL?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic \u003Cbr> CrossCity | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> DiDiCD \u003Cbr> DiDiSZ | pFedCTP | [Personalized Federated Learning for Cross-City Traffic Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F611) | [Code](https:\u002F\u002Fgithub.com\u002FZYuSdu\u002FpFedCTP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZYuSdu\u002FpFedCTP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZYuSdu\u002FpFedCTP?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SDformer | [SDformer: Transformer with Spectral Filter and Dynamic Attention for Multivariate Time Series Long-term Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F629) | [Code](https:\u002F\u002Fgithub.com\u002Fzhouziyu02\u002FSDformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhouziyu02\u002FSDformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhouziyu02\u002FSDformer?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SpecAR-Net | [SpecAR-Net: Spectrogram Analysis and Representation Network for Time Series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F433) | [Code](https:\u002F\u002Fgithub.com\u002FDongyi2go\u002FSpecAR_Net) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDongyi2go\u002FSpecAR_Net?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDongyi2go\u002FSpecAR_Net?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | [TimesNet](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) | SCAT | [SCAT: A Time Series Forecasting with Spectral Central Alternating Transformers](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F622) | None | IJCAI\u003Cbr>2024\n| Traffic | Traffic \u003Cbr> ECG \u003Cbr> COVID-19 \u003Cbr> Wiki \u003Cbr> Solar | DIAN | [Decoupled Invariant Attention Network for Multivariate Time-series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F275) | [Code](https:\u002F\u002Fgithub.com\u002Fxhh39\u002FDIAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxhh39\u002FDIAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxhh39\u002FDIAN?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Traffic | Wave \u003Cbr> Wind \u003Cbr> Air | EPL | [Self-adaptive Extreme Penalized Loss for Imbalanced Time Series Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2024\u002F568) | [Code](https:\u002F\u002Fgithub.com\u002FLdiper\u002FEPL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLdiper\u002FEPL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLdiper\u002FEPL?color=critical&style=social) | IJCAI\u003Cbr>2024\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> Exchange | U-Mixer | [U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29337) | None | AAAI\u003Cbr>2024\n| Irregular |USHCN \u003Cbr> MIMIC-III \u003Cbr> MIMIC-IV \u003Cbr> Physionet-12 | GraFITi | [GraFITi: Graphs for Forecasting Irregularly Sampled Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29560) | [Code](https:\u002F\u002Fgithub.com\u002Fyalavarthivk\u002FGraFITi) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyalavarthivk\u002FGraFITi?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyalavarthivk\u002FGraFITi?color=critical&style=social) | AAAI\u003Cbr>2024\n| Traffic \u003Cbr> Flow | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | MultiSPANS | [MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635820) | [Code](https:\u002F\u002Fgithub.com\u002FSELGroup\u002FMultiSPANS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSELGroup\u002FMultiSPANS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSELGroup\u002FMultiSPANS?color=critical&style=social) | WSDM 2024\n| Multivariat | SIP \u003Cbr> NYC \u003Cbr> METR-LA | CreST | [CreST: A Credible Spatiotemporal Learning Framework for Uncertainty-aware Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635759) | None | WSDM 2024\n| Multivariat | Web Traffic \u003Cbr> Labour \u003Cbr> Traffic \u003Cbr> Tourism | HTS | [NeuralReconciler for Hierarchical Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635806) | None | WSDM 2024\n| Multivariat | NYC13 \u003Cbr> BikeNYC \u003Cbr> Chicago21 \u003Cbr> Chicago22 | CityCAN | [CityCAN: Causal Attention Network for Citywide Spatio-Temporal Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3616855.3635764) | None | WSDM 2024\n| Multivariat | Solar \u003Cbr> Wiki \u003Cbr> Traffic \u003Cbr> ECG \u003Cbr> Electricity \u003Cbr> COVID-19 \u003Cbr> Weather \u003Cbr> ETT | FreTS | [Frequency-domain MLPs are More Effective Learners in Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Ff1d16af76939f476b5f040fd1398c0a3-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Faikunyi\u002FFreTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faikunyi\u002FFreTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faikunyi\u002FFreTS?color=critical&style=social) | NIPS\u003Cbr>2023\n| LLM4TS \u003Cbr> Zero Shot | Darts \u003Cbr> Monash \u003Cbr> Informer | - | [Large Language Models Are Zero-Shot Time Series Forecasters](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F3eb7ca52e8207697361b2c0fb3926511-Abstract-Conference.html) | [LLM](https:\u002F\u002Fgithub.com\u002Fngruver\u002Fllmtime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fngruver\u002Fllmtime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fngruver\u002Fllmtime?color=critical&style=social) | NIPS\u003Cbr>2023\n| Zero Shot | ECL \u003Cbr>ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Traffic \u003Cbr> Weather | ForecastPFN | [ForecastPFN: Synthetically-Trained Zero-Shot Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F0731f0e65559059eb9cd9d6f44ce2dd8-Abstract-Conference.html) | [TF](https:\u002F\u002Fgithub.com\u002Fabacusai\u002Fforecastpfn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fabacusai\u002Fforecastpfn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fabacusai\u002Fforecastpfn?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ECL \u003Cbr> Traffic \u003Cbr>ETT \u003Cbr> Weather | WITRAN | [WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F2938ad0434a6506b125d8adaff084a4a-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002FWater2sea\u002FWITRAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWater2sea\u002FWITRAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWater2sea\u002FWITRAN?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | Neural Lad | [Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling](https:\u002F\u002Fopenreview.net\u002Fforum?id=bISkJSa5Td) | None | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity | OneNet | [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fdd6a47bc0aad6f34aa5e77706d90cdc4-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fyfzhang114\u002FOneNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyfzhang114\u002FOneNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyfzhang114\u002FOneNet?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat \u003Cbr> Solar Irradiance| CAB \u003Cbr> TAM | CrossViVit | [Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context](https:\u002F\u002Fopenreview.net\u002Fforum?id=x5ZruOa4ax) | [Code](https:\u002F\u002Fgithub.com\u002Fgitbooo\u002FCrossViVit) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgitbooo\u002FCrossViVit?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgitbooo\u002FCrossViVit?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ECL \u003Cbr>ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Traffic \u003Cbr> Weather | Koopa | [Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fdd6a47bc0aad6f34aa5e77706d90cdc4-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FKoopa) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FKoopa?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FKoopa?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | GPVAR \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> CER-E\u003Cbr>AQI | TTS-IMP | [Taming Local Effects in Graph-based Spatiotemporal Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=x2PH6q32LR) | [Code](https:\u002F\u002Fgithub.com\u002FGraph-Machine-Learning-Group\u002Ftaming-local-effects-stgnns) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-Machine-Learning-Group\u002Ftaming-local-effects-stgnns?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-Machine-Learning-Group\u002Ftaming-local-effects-stgnns?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | PEMS08 \u003Cbr> AIR-BJ \u003Cbr> AIR-GZ | CaST | [Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment](https:\u002F\u002Fopenreview.net\u002Fforum?id=17Zkztjlgt) | [Code](https:\u002F\u002Fgithub.com\u002Fyutong-xia\u002FCaST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyutong-xia\u002FCaST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyutong-xia\u002FCaST?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | PEMS08 \u003Cbr> METR-LA \u003Cbr> NYC Taxi \u003Cbr> NYC Bike | GPT-ST | [GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=nMH5cUaSj8) | [Code](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FGPT-ST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHKUDS\u002FGPT-ST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHKUDS\u002FGPT-ST?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | Solar \u003Cbr> Wiki \u003Cbr> Traffic \u003Cbr> COVID-19 | FourierGNN | [FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fdc1e32dd3eb381dbc71482f6a96cbf86-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Faikunyi\u002FFourierGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faikunyi\u002FFourierGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faikunyi\u002FFourierGNN?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic | SimMTM | [SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F5f9bfdfe3685e4ccdbc0e7fb29cccf2a-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FSimMTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FSimMTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FSimMTM?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | BasisFormer | [BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fe150e6d0a1e5214740c39c6e4503ba7a-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fnzl5116190\u002FBasisformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnzl5116190\u002FBasisformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnzl5116190\u002FBasisformer?color=critical&style=social) | NIPS\u003Cbr>2023\n| Irregular | Neonate \u003Cbr> Traffic \u003Cbr> MIMIC \u003Cbr> StackOverflow \u003Cbr> BookOrder \u003Cbr> Exchange \u003Cbr> ETT \u003Cbr> ILI\u003Cbr> Weather| ContiFormer | [ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F9328208f88ec69420031647e6ff97727-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FSeqML\u002Ftree\u002Fmain\u002FContiFormer) | NIPS\u003Cbr>2023\n| Multivariat | Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> ETT | SAN | [Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F2e19dab94882bc95ed094c4399cfda02-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Ficantnamemyself\u002FSAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ficantnamemyself\u002FSAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ficantnamemyself\u002FSAN?color=critical&style=social) | NIPS\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | DeepTime | [ Learning Deep Time-index Models for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=pgcfCCNQXO) | [Code](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002FDeepTime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsalesforce\u002FDeepTime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsalesforce\u002FDeepTime?color=critical&style=social) | ICML\u003Cbr>2023\n| Multivariat | Crime \u003Cbr> CHI-Taxi \u003Cbr> NYC-Bike \u003Cbr> NYC-Taxi\u003Cbr> CHI-House\u003Cbr> NYC-House | GraphST | [Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation](https:\u002F\u002Fopenreview.net\u002Fforum?id=LVARH5wXM9) | [Code](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FGraphST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHKUDS\u002FGraphST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHKUDS\u002FGraphST?color=critical&style=social) | ICML\u003Cbr>2023\n| Multivariat | Synthetic \u003Cbr> Taxi \u003Cbr> Electricity \u003Cbr> Traffic | FeatureP | [Feature Programming for Multivariate Time Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=LVARH5wXM9) | [Code](https:\u002F\u002Fgithub.com\u002FSirAlex900\u002FFeatureProgramming) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSirAlex900\u002FFeatureProgramming?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSirAlex900\u002FFeatureProgramming?color=critical&style=social) | ICML\u003Cbr>2023\n| Multivariat | NorPool \u003Cbr> Caiso \u003Cbr> Weather \u003Cbr> ETT \u003Cbr> Wind \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Exchange | TimeDiff | [Non-autoregressive Conditional Diffusion Models for Time Series Prediction](https:\u002F\u002Fopenreview.net\u002Fforum?id=wZsnZkviro) | None| ICML\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | MICN | [MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=zt53IDUR1U) | [Code](https:\u002F\u002Fgithub.com\u002Fwanghq21\u002FMICN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwanghq21\u002FMICN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwanghq21\u002FMICN?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> ILI \u003Cbr> Traffic | Crossformer | [Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vSVLM2j9eie) | [Code](https:\u002F\u002Fgithub.com\u002FThinklab-SJTU\u002FCrossformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FThinklab-SJTU\u002FCrossformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FThinklab-SJTU\u002FCrossformer?color=critical&style=social) | ICLR\u003Cbr>2023\n| Forecast \u003Cbr> Imputation \u003Cbr> Classifi \u003Cbr> AnomalyDet | ETT \u003Cbr> M4 \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr>SMD,MSL \u003Cbr> SMAP,SWaT \u003Cbr> PSM | TimesNet | [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https:\u002F\u002Fopenreview.net\u002Fforum?id=ju_Uqw384Oq) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FTime-Series-Library?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FTime-Series-Library?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | | Meta-SSM | [Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=7C9aRX2nBf2) | [Code](https:\u002F\u002Fgithub.com\u002Fjohn-x-jiang\u002Fmeta_ssm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjohn-x-jiang\u002Fmeta_ssm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjohn-x-jiang\u002Fmeta_ssm?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Weather | FSNet | [Learning Fast and Slow for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=q-PbpHD3EOk) | [Code](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Ffsnet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsalesforce\u002Ffsnet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsalesforce\u002Ffsnet?color=critical&style=social) | ICLR\u003Cbr>2023\n| Robust \u003Cbr> Multivariat | Traffic \u003Cbr> Taxi \u003Cbr> Wiki \u003Cbr> Electricity | | [Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms](https:\u002F\u002Fopenreview.net\u002Fforum?id=ctmLBs8lITa) | [Amazon](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluonts\u002Ftree\u002Fdev\u002Fsrc\u002Fgluonts\u002Fnursery) | ICLR\u003Cbr>2023\n| Multivariat | Electricity \u003Cbr> Crypto \u003Cbr> M4 \u003Cbr> Traffic \u003Cbr> Exchange | KNF | [Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts](https:\u002F\u002Fopenreview.net\u002Fforum?id=kUmdmHxK5N) | [Code](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002FKNF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002FKNF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002FKNF?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Exchange | SpaceTime | [Effectively Modeling Time Series with Simple Discrete State Spaces](https:\u002F\u002Fopenreview.net\u002Fforum?id=2EpjkjzdCAa) | [Code](https:\u002F\u002Fgithub.com\u002FHazyResearch\u002Fspacetime) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHazyResearch\u002Fspacetime?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHazyResearch\u002Fspacetime?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | Weather \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> ILI \u003Cbr> ETT | PatchTST | [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https:\u002F\u002Fopenreview.net\u002Fforum?id=Jbdc0vTOcol) | [Code](https:\u002F\u002Fgithub.com\u002Fyuqinie98\u002FPatchTST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuqinie98\u002FPatchTST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuqinie98\u002FPatchTST?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat | Exchange \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> ILI | Scaleformer | [Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=sCrnllCtjoE) | [Code](https:\u002F\u002Fgithub.com\u002FBorealisAI\u002Fscaleformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBorealisAI\u002Fscaleformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBorealisAI\u002Fscaleformer?color=critical&style=social) | ICLR\u003Cbr>2023\n| Multivariat \u003Cbr> classification \u003Cbr> AnomalyDec | Electricity \u003Cbr> Weather \u003Cbr> ETTm1 \u003Cbr> MSL \u003Cbr> SMD \u003Cbr> SMAP | SBT | [Sparse Binary Transformers for Multivariate Time Series Modeling](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3580305.3599508) | [Code](https:\u002F\u002Fgithub.com\u002Fmattgorb\u002Fsparse-binary-transformers) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmattgorb\u002Fsparse-binary-transformers?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmattgorb\u002Fsparse-binary-transformers?color=critical&style=social) | KDD\u003Cbr>2023\n| Multivariat | SIP \u003Cbr> METR-LA \u003Cbr> KnowAir \u003Cbr> Electricity | CauSTG | [Maintaining the Status Quo: Capturing Invariant Relations for OOD Spatiotemporal Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | [Code](https:\u002F\u002Fgithub.com\u002Fzzyy0929\u002FKDD23-CauSTG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzzyy0929\u002FKDD23-CauSTG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzzyy0929\u002FKDD23-CauSTG?color=critical&style=social) | KDD\u003Cbr>2023\n| Robust \u003Cbr> Multivariat | PEMS-BAY \u003Cbr> PEMS04 | RDAT | [Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599492) | [Code](https:\u002F\u002Fgithub.com\u002Fusail-hkust\u002FRDAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fusail-hkust\u002FRDAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fusail-hkust\u002FRDAT?color=critical&style=social) | KDD\u003Cbr>2023\n| Multivariat | Beijing \u003Cbr> Chengdu \u003Cbr> Harbin | Frigate | [Frigate: Frugal Spatio-temporal Forecasting on Road Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599357) | [Code](https:\u002F\u002Fgithub.com\u002Fidea-iitd\u002Ffrigate) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fidea-iitd\u002Ffrigate?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fidea-iitd\u002Ffrigate?color=critical&style=social) | KDD\u003Cbr>2023\n|Multivariat | XC-Traffic \u003Cbr> NYC-Traffic | GCIM | [Generative Causal Interpretation Model for Spatio-Temporal Representation Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599363) | None | KDD\u003Cbr>2023\n| Multivariat | Tourism \u003Cbr> Labour \u003Cbr> Wiki \u003Cbr> Flu-Symptoms \u003Cbr> FB-Survey | PROFHiT | [When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FProfhit) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FProfhit?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FProfhit?color=critical&style=social) | KDD\u003Cbr>2023\n| Multivariat \u003Cbr> Under Miss | AQI-36 \u003Cbr> AQI \u003Cbr> PEMS-BAY \u003Cbr> CER-E \u003Cbr> Healthcare \u003Cbr> SMAP | MIDM | [An Observed Value Consistent Diffusion Model for Imputing Missing Values in Multivariate Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599257) | [Author](http:\u002F\u002Fhome.ustc.edu.cn\u002F~wx309\u002F) | KDD\u003Cbr>2023\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> etc.| Localised | [Localised Adaptive Spatial-Temporal Graph Neural Network](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599418) | None | KDD\u003Cbr>2023\n| Multivariat | PEMS3-Stream | PECPM | [Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599463) | None | KDD\u003Cbr>2023\n| Multivariat | Tourism \u003Cbr> Wiki \u003Cbr> Traffic | HPO | [Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | None | KDD\u003Cbr>2023 \n| Multivariat | Weather \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> ETT | TSMixer | [TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599533) | None| KDD\u003Cbr>2023\n| Transfer \u003Cbr> Traffic \u003Cbr> Forecasting | PEMSD7M \u003Cbr> PEMSD7M \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | TransGTR | [Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599529) | [Author](https:\u002F\u002Fgithub.com\u002FKL4805) | KDD\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Weather \u003Cbr> ILI | DLinear | [Are Transformers Effective for Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26317) | [Code](https:\u002F\u002Fgithub.com\u002Fcure-lab\u002FLTSF-Linear) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcure-lab\u002FLTSF-Linear?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcure-lab\u002FLTSF-Linear?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> PEMSD7M | STC-Dropout | [Easy Begun Is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25590) | [Code](https:\u002F\u002Fgithub.com\u002FUrban-Computing\u002FSTC-Dropout) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUrban-Computing\u002FSTC-Dropout?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUrban-Computing\u002FSTC-Dropout?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | BJ-Bike \u003Cbr> NYC-Bike | STNSCM | [Spatio-Temporal Neural Structural Causal Models for Bike Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25542) | [Code](https:\u002F\u002Fgithub.com\u002FEternityZY\u002FSTNSCM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEternityZY\u002FSTNSCM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEternityZY\u002FSTNSCM?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | XC-Trans \u003Cbr> XC-Speed | CCHMM | [Causal Conditional Hidden Markov Model for Multimodal Traffic Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25619) | [Code](https:\u002F\u002Fgithub.com\u002FEternityZY\u002FCCHMM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEternityZY\u002FCCHMM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEternityZY\u002FCCHMM?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | NYCBike1 \u003Cbr> NYCBike2 \u003Cbr> NYCTaxi \u003Cbr> BJTaxi | ST-SSL | [Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25555) | [Code](https:\u002F\u002Fgithub.com\u002FEcho-Ji\u002FST-SSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEcho-Ji\u002FST-SSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEcho-Ji\u002FST-SSL?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | PV-US \u003Cbr> CER-En | SGP | [Scalable Spatiotemporal Graph Neural Networks](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25880) | [Code](https:\u002F\u002Fgithub.com\u002FGraph-Machine-Learning-Group\u002Fsgp) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-Machine-Learning-Group\u002Fsgp?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-Machine-Learning-Group\u002Fsgp?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | Electricity \u003Cbr> Solar \u003Cbr> PEMS-BAY \u003Cbr> METR-LA | SRD | [Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25915) | [Code](https:\u002F\u002Fgithub.com\u002FArthur-Null\u002FSRD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FArthur-Null\u002FSRD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FArthur-Null\u002FSRD?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity | InfoTS | [Time Series Contrastive Learning with Information-Aware Augmentations](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25575) | [Code](https:\u002F\u002Fgithub.com\u002Fchengw07\u002FInfoTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchengw07\u002FInfoTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchengw07\u002FInfoTS?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | PhysioNet \u003Cbr> MIMIC-III \u003Cbr> Activity \u003Cbr> Appliances Energy | PrimeNet | [PrimeNet: Pre-training for Irregular Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25876) | [Code](https:\u002F\u002Fgithub.com\u002Franakroychowdhury\u002FPrimeNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Franakroychowdhury\u002FPrimeNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Franakroychowdhury\u002FPrimeNet?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | Electricity \u003Cbr> ETT \u003Cbr> Weather | Dish-TS | [Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25914) | [Code](https:\u002F\u002Fgithub.com\u002Fweifantt\u002FDish-TS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fweifantt\u002FDish-TS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fweifantt\u002FDish-TS?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | NHITS | [NHITS: Neural Hierarchical Interpolation for Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25854) | [Code](https:\u002F\u002Fgithub.com\u002FNixtla\u002Fneuralforecast) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNixtla\u002Fneuralforecast?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNixtla\u002Fneuralforecast?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> ETT \u003Cbr> Weather | MegaCRN | [Spatio-Temporal Meta-Graph Learning for Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25976) | [Code](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FMegaCRN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa20\u002FMegaCRN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa20\u002FMegaCRN?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | Santa \u003Cbr> Traffic | NEC+ | [An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26276) | [Code](https:\u002F\u002Fgithub.com\u002Fdavidanastasiu\u002FNECPlus) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdavidanastasiu\u002FNECPlus?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdavidanastasiu\u002FNECPlus?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Extreme MTSF | Electricity \u003Cbr> Solar \u003Cbr> Weather \u003Cbr> Traffic | WaveForM | [WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26276) | [Code](https:\u002F\u002Fgithub.com\u002FalanyoungCN\u002FWaveForM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FalanyoungCN\u002FWaveForM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FalanyoungCN\u002FWaveForM?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> NYCTaxi \u003Cbr> CHBike \u003Cbr> TDrive | PDFormer | [PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25556) | [Code](https:\u002F\u002Fgithub.com\u002FBUAABIGSCity\u002FPDFormer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBUAABIGSCity\u002FPDFormer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBUAABIGSCity\u002FPDFormer?color=critical&style=social) | AAAI\u003Cbr>2023 \n| Multivariat | AmapBeijing \u003Cbr> AmapChengdu | STGNPP | [Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26669) | None | AAAI\u003Cbr>2023\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | InParformer | [InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25845) | None | AAAI\u003Cbr>2023\n| Multivariat | Tourism \u003Cbr> Labour \u003Cbr> M5 | SLOTH | [SLOTH: Structured Learning and Task-Based Optimization for Time Series Forecasting on Hierarchies](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26350) | None | AAAI\u003Cbr>2023 \n| Multivariat | Wind \u003Cbr> Solar | eForecaster | [eForecaster: Unifying Electricity Forecasting with Robust, Flexible, and Explainable Machine Learning Algorithms](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26853) | None | AAAI\u003Cbr>2023 \n| Multivariat | NYCTaxi \u003Cbr> PEMS04 | AutoSTL | [AutoSTL: Automated Spatio-Temporal Multi-Task Learning](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25616) | None | AAAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> PEMS-BAY | Trafformer | [Trafformer: Unify Time and Space in Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1609\u002Faaai.v37i7.25980) | None| AAAI\u003Cbr>2023\n| Multivariat | Electricity \u003Cbr> PM2.5 \u003Cbr> Exchange | DeLELSTM | [DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F478) | [Code](https:\u002F\u002Fgithub.com\u002Fwangcq01\u002FDeLELSTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwangcq01\u002FDeLELSTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwangcq01\u002FDeLELSTM?color=critical&style=social) | IJCAI\u003Cbr>2023 \n| Multivariat | NYC-Bike \u003Cbr> PEMS-BAY \u003Cbr> PEMS08 | ReMo | [Not Only Pairwise Relationships: Fine-Grained Relational Modeling for Multivariate Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F491) | [Code](https:\u002F\u002Fgithub.com\u002Fbeginner-sketch\u002Fgmrl) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbeginner-sketch\u002Fgmrl?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbeginner-sketch\u002Fgmrl?color=critical&style=social) | IJCAI\u003Cbr>2023 \n| Multivariat | NASA | MetePFL | [Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F393) | [Code](https:\u002F\u002Fgithub.com\u002Fshengchaochen82\u002FMetePFL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshengchaochen82\u002FMetePFL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshengchaochen82\u002FMetePFL?color=critical&style=social) | IJCAI\u003Cbr>2023 \n| Multivariat | Hurricane \u003Cbr> Climate | Self-Recover | [Self-Recover: Forecasting Block Maxima in Time Series from Predictors with Disparate Temporal Coverage Using Self-Supervised Learning](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F4141) | None | IJCAI\u003Cbr>2023 \n| Multivariat | Weather \u003Cbr> Traffc \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> ILI | SMARTformer | [SMARTformer: Semi-Autoregressive Transformer with Efficient Integrated Window Attention for Long Time Series Forecasting](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F241) | None| IJCAI\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> Beijing \u003Cbr> Xiamen | INCREASE | [INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3543507.3583525) | [TF](https:\u002F\u002Fgithub.com\u002Fzhengchuanpan\u002FINCREASE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhengchuanpan\u002FINCREASE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhengchuanpan\u002FINCREASE?color=critical&style=social) | WWW 2023\n| Multivariat | MQPS \u003Cbr> ETT \u003Cbr> Electricity | KAE-Informer | [KAE-Informer: A Knowledge Auto-Embedding Informer for Forecasting Long-Term Workloads of Microservices](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3543507.3583288) | [Code](https:\u002F\u002Fgithub.com\u002Fcitsjtu2020\u002FKAE-Informer-MQPS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) | WWW 2023\n| Multivariat | Typhoon-JP \u003Cbr> COVID-JP \u003Cbr> Hurricane-US | MemeSTN | [Learning Social Meta-knowledge for Nowcasting Human Mobility in Disaster](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3543507.3583991) | [Code](https:\u002F\u002Fgithub.com\u002Fcitsjtu2020\u002FKAE-Informer-MQPS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcitsjtu2020\u002FKAE-Informer-MQPS?color=critical&style=social) | WWW 2023\n| Multivariat | NYC \u003Cbr> Chicago | EALGAP | [Extreme-Aware Local-Global Attention for Spatio-Temporal Urban Mobility Learning](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184645) | [Keras](https:\u002F\u002Fgithub.com\u002FHuiqunHuang\u002FEALGAP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHuiqunHuang\u002FEALGAP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHuiqunHuang\u002FEALGAP?color=critical&style=social) | ICDE 2023 \n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DyHSL | [Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184800) | [Code](https:\u002F\u002Fgithub.com\u002FYushengZhao\u002FDyHSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYushengZhao\u002FDyHSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYushengZhao\u002FDyHSL?color=critical&style=social) | ICDE 2023 \n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STWave | [When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184591) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FSTWave) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FSTWave?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FSTWave?color=critical&style=social) | ICDE 2023 \n| Multivariat | Seattle \u003Cbr> PEMS04 \u003Cbr> PEMS08 | SSTBAN | [Self-Supervised Spatial-Temporal Bottleneck Attentive Network for Efficient Long-term Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184658) | [Code](https:\u002F\u002Fgithub.com\u002FguoshnBJTU\u002FSSTBAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FguoshnBJTU\u002FSSTBAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FguoshnBJTU\u002FSSTBAN?color=critical&style=social) | ICDE 2023 \n| Multivariat | PEMSD4 \u003Cbr> PEMSD8 \u003Cbr> AirBJ \u003Cbr> TrafficSIP | MGTF | [A Multi-graph Fusion Based Spatiotemporal Dynamic Learning Framework](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3539597.3570396) | [Author](http:\u002F\u002Fhome.ustc.edu.cn\u002F~wx309\u002F) | WSDM 2023\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08| STAEformer | [Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615136) | [Code](https:\u002F\u002Fgithub.com\u002FXDZhelheim\u002FSTAEformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FXDZhelheim\u002FSTAEformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FXDZhelheim\u002FSTAEformer?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Traffic | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | TrendGCN | [Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614868) | [Code](https:\u002F\u002Fgithub.com\u002Fjuyongjiang\u002FTrendGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjuyongjiang\u002FTrendGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjuyongjiang\u002FTrendGCN?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Exchange | GCformer | [GCformer: An Efficient Solution for Accurate and Scalable Long-Term Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614868) | [Code](https:\u002F\u002Fgithub.com\u002FYanjun-Zhao\u002FGCformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYanjun-Zhao\u002FGCformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYanjun-Zhao\u002FGCformer?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic | Seq2Peak | [Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615159) | [Code](https:\u002F\u002Fgithub.com\u002Fzhangzw16\u002FSeq2Peak) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhangzw16\u002FSeq2Peak?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhangzw16\u002FSeq2Peak?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> NYC Crime \u003Cbr> CHI Crime | CL4ST | [Spatio-Temporal Meta Contrastive Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615065) | [Code](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FCL4ST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHKUDS\u002FCL4ST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHKUDS\u002FCL4ST?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | NYC Bike \u003Cbr> NYC Taxi | MLPST | [MLPST: MLP is All You Need for Spatio-Temporal Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614969) | [Author](https:\u002F\u002Fgithub.com\u002FZhang-Zijian) | CIKM\u003Cbr>2023 \n| Multivariat | TaxiBJ \u003Cbr> BikeNYC | MC-STL | [Mask- and Contrast-Enhanced Spatio-Temporal Learning for Urban Flow Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614958) | [Code](https:\u002F\u002Fgithub.com\u002FCodeZx6\u002FMCSTL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCodeZx6\u002FMCSTL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCodeZx6\u002FMCSTL?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | PeMS \u003Cbr> Beijing \u003Cbr> Electricity \u003Cbr> COVID-CHI | MemDA | [MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615136) | [Code](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FUrban_Concept_Drift) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa20\u002FUrban_Concept_Drift?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa20\u002FUrban_Concept_Drift?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Cross City \u003Cbr> Traffic | PEMS-BAY \u003Cbr> METR-LA \u003Cbr> Chengdu \u003Cbr> Shenzhen| TPB | [Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614829) | [Code](https:\u002F\u002Fgithub.com\u002Fzhyliu00\u002FTPB) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhyliu00\u002FTPB?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhyliu00\u002FTPB?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMSD7M | UAGCRN | [Enhancing Spatio-temporal Traffic Prediction through Urban Human Activity Analysis](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614867) | [TF](https:\u002F\u002Fgithub.com\u002FSuminHan\u002FTraffic-UAGCRNTF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSuminHan\u002FTraffic-UAGCRNTF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSuminHan\u002FTraffic-UAGCRNTF?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | Complaint \u003Cbr> NYC Taxi | PromptST | [PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615159) | [Code](https:\u002F\u002Fgithub.com\u002FZhang-Zijian\u002FPromptST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhang-Zijian\u002FPromptST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZhang-Zijian\u002FPromptST?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS08 | HIEST | [Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614910) | [Code](https:\u002F\u002Fgithub.com\u002FVAN-QIAN\u002FCIKM23-HIEST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVAN-QIAN\u002FCIKM23-HIEST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVAN-QIAN\u002FCIKM23-HIEST?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Traffic | TemDep | [TemDep: Temporal Dependency Priority for Multivariate Time Series Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615164) | [Code](https:\u002F\u002Fgithub.com\u002Fzivgogogo\u002FTemDep) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzivgogogo\u002FTemDep?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzivgogogo\u002FTemDep?color=critical&style=social) | CIKM\u003Cbr>2023 \n| Traffic | BJ-Center \u003Cbr> METR-LA | ST-MoE | [ST-MoE: Spatio-Temporal Mixture-of-Experts for Debiasing in Traffic Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615068) | None | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> Traffic \u003Cbr> Exchange | AVGNets | [Learning Visibility Attention Graph Representation for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615289) | None | CIKM\u003Cbr>2023 \n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STGBN | [Spatial-Temporal Graph Boosting Networks: Enhancing Spatial-Temporal Graph Neural Networks via Gradient Boosting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615066) | None | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> ILI \u003Cbr> Exchange | FAMC-Net | [FAMC-Net: Frequency Domain Parity Correction Attention and Multi-Scale Dilated Convolution for Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614876) | None| CIKM\u003Cbr>2023 \n| Cross City \u003Cbr> Traffic | NYC \u003Cbr> Chicago \u003Cbr> Nashville | CARPG | [CARPG: Cross-City Knowledge Transfer for Traffic Accident Prediction via Attentive Region-Level Parameter Generation](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3614802) | None| CIKM\u003Cbr>2023 \n| Traffic | SPEED \u003Cbr> FLOW | CANet | [Clustering-property Matters: A Cluster-aware Network for Large Scale Multivariate Time Series Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615253) | None | CIKM\u003Cbr>2023 \n| Multivariat | ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Weather \u003Cbr> Electricity \u003Cbr> Traffic | DSformer | [DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3614851) | None | CIKM\u003Cbr>2023 \n| Multivariat | Wufu | MODE | [Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615487) | None | CIKM\u003Cbr>2023 \n| Multivariat | NYC | MetaRSTP | [Region Profile Enhanced Urban Spatio-Temporal Prediction via Adaptive Meta-Learning](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615027) | None | CIKM\u003Cbr>2023 \n| Multivariat | SIP \u003Cbr> NYC \u003Cbr> METR-LA | G2S | [Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch22) | None | SDM 2023\n| Multivariat | Solar \u003Cbr> PEMS-BAY \u003Cbr> Electricity | ERL | [Time-delayed Multivariate Time Series Predictions](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch37) | None | SDM 2023\n| Multivariat | Weather2K | Weather2K | [Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations](https:\u002F\u002Fproceedings.mlr.press\u002Fv206\u002Fzhu23a.html) | [Weather2K](https:\u002F\u002Fgithub.com\u002Fbycnfz\u002Fweather2k\u002F) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbycnfz\u002Fweather2k?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbycnfz\u002Fweather2k?color=critical&style=social) | AISTATS 2023 \n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | FiLM | [FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=zTQdHSQUQWc) | [Code](https:\u002F\u002Fgithub.com\u002Ftianzhou2011\u002FFiLM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftianzhou2011\u002FFiLM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftianzhou2011\u002FFiLM?color=critical&style=social) | NeurIPS 2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Weather | LaST | [Learning Latent Seasonal-Trend Representations for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=C9yUwd72yy) | [Code](https:\u002F\u002Fgithub.com\u002Fzhycs\u002FLaST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhycs\u002FLaST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhycs\u002FLaST?color=critical&style=social) | NeurIPS 2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | WaveBound | [WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=vsNQkquutZk) | [Code](https:\u002F\u002Fgithub.com\u002Fchoyi0521\u002FWaveBound) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchoyi0521\u002FWaveBound?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchoyi0521\u002FWaveBound?color=critical&style=social) | NeurIPS 2022\n| Multivariat | COVID-19 \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> Temperature \u003Cbr> Bytom \u003Cbr> Wind | ZFC-SHCN | [Time-Conditioned Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=2Ln-TWxVtf) | [Future](https:\u002F\u002Fgithub.com\u002Fzfcshcn\u002FZFC-SHCN) | NeurIPS 2022\n| Multivariat | ETT \u003Cbr> Traffic \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | SCINet | [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https:\u002F\u002Fopenreview.net\u002Fforum?id=AyajSjTAzmg) | [Code](https:\u002F\u002Fgithub.com\u002Fcure-lab\u002FSCINet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcure-lab\u002FSCINet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcure-lab\u002FSCINet?color=critical&style=social) | NeurIPS 2022\n| Multivariat | Electricity \u003Cbr> ETT \u003Cbr> Exchange \u003Cbr> ILI \u003Cbr> Traffic \u003Cbr> Weather | NonstaTransf | [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=ucNDIDRNjjv) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FNonstationary_Transformers) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FNonstationary_Transformers?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FNonstationary_Transformers?color=critical&style=social) | NeurIPS 2022\n| Multivariat | Traffic \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> PEMS07(M) \u003Cbr> PEMS-BAY | TPGNN | [Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks](https:\u002F\u002Fopenreview.net\u002Fforum?id=pMumil2EJh) | [Future](https:\u002F\u002Fgithub.com\u002Fzyplanet\u002FTPGNN) | NeurIPS 2022\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DSTAGNN | [DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Flan22a.html) | [Code](https:\u002F\u002Fgithub.com\u002FSYLan2019\u002FDSTAGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSYLan2019\u002FDSTAGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSYLan2019\u002FDSTAGNN?color=critical&style=social) | ICML\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | FEDformer | [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fzhou22g.html) | [Code](https:\u002F\u002Fgithub.com\u002FMAZiqing\u002FFEDformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMAZiqing\u002FFEDformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMAZiqing\u002FFEDformer?color=critical&style=social) | ICML\u003Cbr>2022\n| Multivariat | Traffic \u003Cbr> Electricity \u003Cbr> Wiki \u003Cbr> Sales | DAF | [DAF-Domain Adaptation for Time Series Forecasting via Attention Sharing](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fjin22d.html) | None| ICML\u003Cbr>2022\n| Multivariat | Electricity \u003Cbr> Solar \u003Cbr> Fred MD \u003Cbr> KDD Cup | TACTiS \u003Cbr> (Copulas,\u003Cbr> Trans) | [TACTiS: Transformer-Attentional Copulas for Time Series](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fdrouin22a.html) | [Code](https:\u002F\u002Fgithub.com\u002Fservicenow\u002Ftactis) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fservicenow\u002Ftactis?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fservicenow\u002Ftactis?color=critical&style=social) | ICML\u003Cbr>2022\n| Multivariat | French \u003Cbr> Electricity | AgACI | [Adaptive Conformal Predictions for Time Series](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07282) | [Python,R](https:\u002F\u002Fgithub.com\u002Fmzaffran\u002FAdaptiveConformalPredictionsTimeSeries) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmzaffran\u002FAdaptiveConformalPredictionsTimeSeries?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmzaffran\u002FAdaptiveConformalPredictionsTimeSeries?color=critical&style=social) | ICML\u003Cbr>2022\n| Traffic Speed | NAVER-Seoul \u003Cbr> METR-LA | PM-MemNet \u003Cbr> (Mem,KNN) | [Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=wwDg3bbYBIq) | [Code](https:\u002F\u002Fgithub.com\u002FHyunWookL\u002FPM-MemNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHyunWookL\u002FPM-MemNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHyunWookL\u002FPM-MemNet?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS08 \u003Cbr> COVID-19,etc | TAMP-S2GCNets \u003Cbr> (GCN,AR, \u003Cbr> Topological Features) | [TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=wv6g8fWLX2q) | [Code](https:\u002F\u002Fwww.dropbox.com\u002Fsh\u002Fn0ajd5l0tdeyb80\u002FAABGn-ejfV1YtRwjf_L0AOsNa?dl=0) | ICLR\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather | CoST | [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=PilZY3omXV2) | [Code](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002FCoST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsalesforce\u002FCoST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsalesforce\u002FCoST?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> M4 \u003Cbr> CASIO \u003Cbr> NP | DEPTS | [DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=AJAR-JgNw__) | [Code](https:\u002F\u002Fgithub.com\u002Fweifantt\u002FDEPTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fweifantt\u002FDEPTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fweifantt\u002FDEPTS?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Wind \u003Cbr> App Flow | Pyraformer | [Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=0EXmFzUn5I) | [Code](https:\u002F\u002Fgithub.com\u002Falipay\u002FPyraformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falipay\u002FPyraformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falipay\u002FPyraformer?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> M4 \u003Cbr> Air Quality \u003Cbr> Nasdaq | RevIN | [Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift](https:\u002F\u002Fopenreview.net\u002Fforum?id=cGDAkQo1C0p) | [Code](https:\u002F\u002Fgithub.com\u002Fts-kim\u002FRevIN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fts-kim\u002FRevIN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fts-kim\u002FRevIN?color=critical&style=social) | ICLR\u003Cbr>2022\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS08 | D2STGNN | [Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting](https:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol15\u002Fp2733-shao.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Fzezhishao\u002FD2STGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzezhishao\u002FD2STGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzezhishao\u002FD2STGNN?color=critical&style=social) | VLDB 2022\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 | STEP | [Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539396) | [Code](https:\u002F\u002Fgithub.com\u002Fzezhishao\u002FSTEP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzezhishao\u002FSTEP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzezhishao\u002FSTEP?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | Solar \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Wind \u003Cbr> NYCBike \u003Cbr> NYCTaxi | ESG | [Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539274) | [Code](https:\u002F\u002Fgithub.com\u002FLiuZH-19\u002FESG) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiuZH-19\u002FESG?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiuZH-19\u002FESG?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | METR-LA \u003Cbr> Solar \u003Cbr> Traffic \u003Cbr> ECG5000 | VSF | [Multi-Variate Time Series Forecasting on Variable Subsets](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539394) | [Code,dgl](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fvsf-time-series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgoogle\u002Fvsf-time-series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgoogle\u002Fvsf-time-series?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | DC Bike \u003Cbr> DC Taxi | CrossTReS | [Selective Cross-City Transfer Learning for Traffic Prediction via Source City Region Re-Weighting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539250) | [Code,dgl](https:\u002F\u002Fgithub.com\u002FKL4805\u002FCrossTReS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKL4805\u002FCrossTReS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKL4805\u002FCrossTReS?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Electricity | Quatformer | [Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539234) | [MRA-BGCN Author](https:\u002F\u002Fscholar.google.com\u002Fcitations?hl=zh-CN&user=dMg_soMAAAAJ&view_op=list_works&sortby=pubdate) \u003Cbr> None Code | KDD\u003Cbr>2022\n| Multivariat | NYCBike \u003Cbr> NYCTaxi \u003Cbr> PEMS03 \u003Cbr> PEMS08 | GMSDR | [MSDR: Multi-Step Dependency Relation Networks for Spatial Temporal Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539397) | [Code](https:\u002F\u002Fgithub.com\u002Fdcliu99\u002FMSDR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdcliu99\u002FMSDR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdcliu99\u002FMSDR?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | Hangzhou \u003Cbr> NYC | DTIGNN | [Modeling Network-level Traffic Flow Transitions on Sparse Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539236) | [Code](https:\u002F\u002Fgithub.com\u002Fshawlen\u002Fdtignn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshawlen\u002Fdtignn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshawlen\u002Fdtignn?color=critical&style=social) | KDD\u003Cbr>2022\n| Multivariat | Temperature \u003Cbr> Cloud cover \u003Cbr> Humidity \u003Cbr> Wind | CLCRN | [Conditional Local Convolution for Spatio-temporal Meteorological Forecasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai1716) | [Code](https:\u002F\u002Fgithub.com\u002FBIRD-TAO\u002FCLCRN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBIRD-TAO\u002FCLCRN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBIRD-TAO\u002FCLCRN?color=critical&style=social) | AAAI\u003Cbr>2022\n| Traffic Flow | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> PEMS07(M) \u003Cbr> PEMS07(L) | STG-NCDE | [Graph Neural Controlled Differential Equations for Traffic Forecasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai6502) | [Code](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FSTG-NCDE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjeongwhanchoi\u002FSTG-NCDE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjeongwhanchoi\u002FSTG-NCDE?color=critical&style=social) | AAAI\u003Cbr>2022\n| Traffic Flow | GT-221 \u003Cbr> WRS-393 \u003Cbr> ZGC-564 | STDEN | [STDEN: Towards Physics-guided Neural Networks for Traffic Flow Prediction](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai211) | [Code](https:\u002F\u002Fgithub.com\u002FEcho-Ji\u002FSTDEN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEcho-Ji\u002FSTDEN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEcho-Ji\u002FSTDEN?color=critical&style=social) | AAAI\u003Cbr>2022\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> PEMS07(M) \u003Cbr> METR-LA | CATN | [CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai7403) | None | AAAI\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity | TS2Vec | [TS2Vec: Towards Universal Representation of Time Series](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai8809) | [Code](https:\u002F\u002Fgithub.com\u002Fyuezhihan\u002Fts2vec) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuezhihan\u002Fts2vec?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuezhihan\u002Fts2vec?color=critical&style=social) | AAAI\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Weather | Triformer | [Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F277) | [Code](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002Ftriformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frazvanc92\u002Ftriformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frazvanc92\u002Ftriformer?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | FOGS | [FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F545) | [Code](https:\u002F\u002Fgithub.com\u002Fkevin-xuan\u002FFOGS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkevin-xuan\u002FFOGS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkevin-xuan\u002FFOGS?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | PEMS04 \u003Cbr> PEMS08 \u003Cbr> RPCM | RGSL | [Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F328) | [Code](https:\u002F\u002Fgithub.com\u002Falipay\u002FRGSL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falipay\u002FRGSL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falipay\u002FRGSL?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | Air Quality \u003Cbr> Parking | DMGA | [Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F309) | None | IJCAI\u003Cbr>2022\n| Multivariat | YellowCab \u003Cbr> GreenCab \u003Cbr> Solar | ST-KMRN | [Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F304) | [Author](https:\u002F\u002Fgithub.com\u002Fmengcz13) | IJCAI\u003Cbr>2022\n| Multivariat | NYCTaxi \u003Cbr> NYCBike \u003Cbr> CHIBike \u003Cbr> BJTaxi \u003Cbr> Chengdu| STAN | [When Transfer Learning Meets Cross-City Urban Flow Prediction: Spatio-Temporal Adaptation Matters](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F282) | None | IJCAI\u003Cbr>2022\n| Multivariat | Hurricanes \u003Cbr> Ausgrid \u003Cbr> Weather | DeepExtrema | [DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F413) | [Code](https:\u002F\u002Fgithub.com\u002Fgalib19\u002FDeepExtrema-IJCAI22-) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgalib19\u002FDeepExtrema-IJCAI22-?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgalib19\u002FDeepExtrema-IJCAI22-?color=critical&style=social) | IJCAI\u003Cbr>2022\n| Multivariat | GoogleSymp \u003Cbr> Covid19 \u003Cbr> Power \u003Cbr> Tweet | CAMul | [CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512037) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FCAMul) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FCAMul?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FCAMul?color=critical&style=social) | WWW 2022\n| Multivariat | Electricity \u003Cbr> Stock | MRLF | [Multi-Granularity Residual Learning with Confidence Estimation for Time Series Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512056) | [Code](https:\u002F\u002Fgithub.com\u002FCMLF-git-dev\u002FMRLF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCMLF-git-dev\u002FMRLF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCMLF-git-dev\u002FMRLF?color=critical&style=social) | WWW 2022\n| Multivariat \u003Cbr> Classification \u003Cbr> Forecasting | MuJoCo \u003Cbr> Google Stock | EXIT | [EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512030) | [Code](https:\u002F\u002Fgithub.com\u002Fsheoyon-jhin\u002FEXIT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsheoyon-jhin\u002FEXIT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsheoyon-jhin\u002FEXIT?color=critical&style=social) | WWW 2022\n| Traffic Flow | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | ST-WA | [Towards Spatio- Temporal Aware Traffic Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835586) | [Code](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002FST-WA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frazvanc92\u002FST-WA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frazvanc92\u002FST-WA?color=critical&style=social) | ICDE 2022\n| Mobility \u003Cbr> Prediction | NYC \u003Cbr> Dallas \u003Cbr> Miami | SHIFT | [Translating Human Mobility Forecasting through Natural Language Generation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3488560.3498387) | [Hao Xue](https:\u002F\u002Fgithub.com\u002Fxuehaouwa) | WSDM 2022\n| Traffic Flow | TaxiBJ \u003Cbr> BikeNYC | ST-GSP | [ST-GSP: Spatial-Temporal Global Semantic Representation Learning for Urban Flow Prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498444) | [Code](https:\u002F\u002Fgithub.com\u002Fk51\u002FSTGSP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fk51\u002FSTGSP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fk51\u002FSTGSP?color=critical&style=social) | WSDM 2022\n| Multivariat | Traffic \u003Cbr> Temperature | ReTime | [Retrieval Based Time Series Forecasting](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.13525#) | None| CIKM\u003Cbr>2022\n| Multivariat | Rainfall \u003Cbr> Traffic \u003Cbr> ETT \u003Cbr> Stock \u003Cbr> Climate | DXtreMM | [Deep Extreme Mixture Model for Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557282) | [Code](https:\u002F\u002Fgithub.com\u002FDXtreMM\u002FDXtreMM_TSF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDXtreMM\u002FDXtreMM_TSF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDXtreMM\u002FDXtreMM_TSF?color=critical&style=social) | CIKM\u003Cbr>2022\n| MTS Analysis \u003Cbr> MTS Forecasting \u003Cbr> Anormaly Detection | ETT \u003Cbr> Electricity \u003Cbr> SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT | MARINA | [MARINA: An MLP-Attention Model for Multivariate Time-Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557386) | None| CIKM\u003Cbr>2022\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | ResCAL | [Residual Correction in Real-Time Traffic Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557432) | None | CIKM\u003Cbr>2022\n| Model Selection | | AutoForecast | [AutoForecast: Automatic Time-Series Forecasting Model Selection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557241) | None | CIKM\u003Cbr>2022\n| Traffic Flow | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DastNet | [Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557294) | [Code](https:\u002F\u002Fgithub.com\u002FYihongT\u002FDASTNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYihongT\u002FDASTNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYihongT\u002FDASTNet?color=critical&style=social) | CIKM\u003Cbr>2022\n| Traffic Flow & Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | AutoSTS | [Automated Spatio-Temporal Synchronous Modeling with Multiple Graphs for Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557243) | YongLi THU | CIKM\u003Cbr>2022\n| Traffic Condition | TRCV-BJ \u003Cbr> TRCV-SH \u003Cbr> TRCV-ZZ | DuTraffic | [DuTraffic: Live Traffic Condition Prediction with Trajectory Data and Street Views at Baidu Maps](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557151) | None | CIKM\u003Cbr>2022\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> WTH \u003Cbr> Weather \u003Cbr> ILI \u003Cbr> Exchange | Linear | [Do Simpler Statistical Methods Perform Better in Multivariate Long Sequence Time-Series Forecasting?](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557585) | None | CIKM\u003Cbr>2022\n| Multivariat | Solar \u003Cbr> Traffic \u003Cbr> Electricity \u003Cbr> Exchange | MAGL | [Memory Augmented Graph Learning Networks for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557638) | None | CIKM\u003Cbr>2022\n| Multivariat | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> PEMS-BAY \u003Cbr> Electricity | STID | [Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557702) | [Code](https:\u002F\u002Fgithub.com\u002Fzezhishao\u002FSTID) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzezhishao\u002FSTID?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzezhishao\u002FSTID?color=critical&style=social) | CIKM\u003Cbr>2022\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS04 \u003Cbr> PEMS07 | ASTTN | [Adaptive Graph Spatial-Temporal Transformer Network for Traffic Forecasting](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3511808.3557540) | None | CIKM\u003Cbr>2022\n| Multivariat | Seoul | CGAN | [Context-aware Traffic Flow Forecasting in New Roads](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557566) | None | CIKM\u003Cbr>2022\n| Traffic Flow & Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS-M \u003Cbr> PEMS04 \u003Cbr> PEMS08 | ST-GAT | [ST-GAT: A Spatio-Temporal Graph Attention Network for Accurate Traffic Speed Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557705) | [Author](https:\u002F\u002Fgithub.com\u002FHanyang-HCC-Lab) | CIKM\u003Cbr>2022\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | HOMGNNs | [Higher-Order Masked Graph Neural Networks for Traffic Flow Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027720) | [Code](https:\u002F\u002Fgithub.com\u002Fmaisuiqianxun\u002FHOMGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmaisuiqianxun\u002FHOMGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmaisuiqianxun\u002FHOMGNN?color=critical&style=social) | ICDM 2022\n| Multivariat | M4 \u003Cbr> Electricity \u003Cbr> car-parts | TopAttn | [Topological Attention for Time Series Forecasting](https:\u002F\u002FNeurIPS.cc\u002FConferences\u002F2021\u002FScheduleMultitrack?event=26763) | [Code](https:\u002F\u002Fgithub.com\u002Fplus-rkwitt\u002FTAN)\u003Cbr> \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fplus-rkwitt\u002FTAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fplus-rkwitt\u002FTAN?color=critical&style=social) Future | NeurIPS 2021\n| Multivariat | Rossmann \u003Cbr> M5 \u003Cbr> Wiki | MisSeq | [MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F6b5754d737784b51ec5075c0dc437bf0-Abstract.html) | None | NeurIPS 2021\n| Multivariat | ETT \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> Traffic \u003Cbr> Weather \u003Cbr> ILI | Autoformer | [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=J4gRj6d5Qm) | [Code](https:\u002F\u002Fgithub.com\u002Fthuml\u002FAutoformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuml\u002FAutoformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuml\u002FAutoformer?color=critical&style=social) | NeurIPS 2021\n| Multivariat | PEMS04 \u003Cbr> PEMS08 \u003Cbr> Traffic \u003Cbr> ADI \u003Cbr> M4 ,etc | Error | [Adjusting for Autocorrelated Errors in Neural Networks for Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=tJ_CO8orSI) | [Code](https:\u002F\u002Fgithub.com\u002FDaikon-Sun\u002FAdjustAutocorrelation) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDaikon-Sun\u002FAdjustAutocorrelation?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDaikon-Sun\u002FAdjustAutocorrelation?color=critical&style=social) | NeurIPS 2021\n| Multivariat | Bytom \u003Cbr> Decentraland \u003Cbr> PEMS04 \u003Cbr> PEMS08| Z-GCNETs | [Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fchen21o.html) | [Code](https:\u002F\u002Fgithub.com\u002FZ-GCNETs\u002FZ-GCNETs) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-GCNETs\u002FZ-GCNETs?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZ-GCNETs\u002FZ-GCNETs?color=critical&style=social) | ICML\u003Cbr>2021\n| Multivariat | PEMS07(M) \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | Cov | [Conditional Temporal Neural Processes with Covariance Loss](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fyoo21b.html) | None | ICML\u003Cbr>2021\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PMU | GTS | [Discrete Graph Structure Learning for Forecasting Multiple Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=WEHSlH5mOk) | [Code](https:\u002F\u002Fgithub.com\u002Fchaoshangcs\u002FGTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchaoshangcs\u002FGTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchaoshangcs\u002FGTS?color=critical&style=social) | ICLR\u003Cbr>2021\n| Multivariat | Benz \u003Cbr> Air Quality \u003Cbr> FuelMoisture | framework | [A Transformer-based Framework for Multivariate Time Series Representation Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467401) | [Code](https:\u002F\u002Fgithub.com\u002Fgzerveas\u002Fmvts_transformer) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgzerveas\u002Fmvts_transformer?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgzerveas\u002Fmvts_transformer?color=critical&style=social) | KDD\u003Cbr>2021\n| Federated Multivariat | PEMS-BAY \u003Cbr> METR-LA | CNFGNN | [Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467371) | [Code](https:\u002F\u002Fgithub.com\u002Fmengcz13\u002FKDD2021_CNFGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmengcz13\u002FKDD2021_CNFGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmengcz13\u002FKDD2021_CNFGNN?color=critical&style=social) | KDD\u003Cbr>2021\n| Traffic Speed | PEMS04 \u003Cbr> PEMS08 \u003Cbr> England | DMSTGCN | [Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467275) | [Code](https:\u002F\u002Fgithub.com\u002Fliangzhehan\u002FDMSTGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliangzhehan\u002FDMSTGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliangzhehan\u002FDMSTGCN?color=critical&style=social) | KDD\u003Cbr>2021\n| Traffic Flow | PEMS07(M) \u003Cbr> PEMS07(L) \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STGODE | [Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467430) | [Code](https:\u002F\u002Fgithub.com\u002Fsquare-coder\u002FSTGODE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsquare-coder\u002FSTGODE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsquare-coder\u002FSTGODE?color=critical&style=social) | KDD\u003Cbr>2021\n| Multivariat | BikeNYC \u003Cbr> PEMS07(M) \u003Cbr> Electricity | ST-Norm | [ST-Norm: Spatial and Temporal Normalization for Multi-variate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467330) | [Code](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FST-Norm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJLDeng\u002FST-Norm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJLDeng\u002FST-Norm?color=critical&style=social) | KDD\u003Cbr>2021\n| Multivariat | DiDiXM \u003Cbr> DiDiCD | TrajNet | [TrajNet: A Trajectory-Based Deep Learning Model for Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467236) | None | KDD\u003Cbr>2021\n| Robust Forecasting | MIMIC-III \u003Cbr> USHCN \u003Cbr> KDD-CUP | DGM | [Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16145) | [Code](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | Guangzhou \u003Cbr> Seattle \u003Cbr> HZMetro , etc. | DSARF | [Deep Switching Auto-Regressive Factorization: Application to Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16907) | [Code](https:\u002F\u002Fgithub.com\u002Fostadabbas\u002FDSARF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fostadabbas\u002FDSARF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fostadabbas\u002FDSARF?color=critical&style=social) | AAAI\u003Cbr>2021\n|Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | FC-GAGA | [FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17114) | [TF](https:\u002F\u002Fgithub.com\u002Fboreshkinai\u002Ffc-gaga) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fboreshkinai\u002Ffc-gaga?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fboreshkinai\u002Ffc-gaga?color=critical&style=social) | AAAI\u003Cbr>2021\n|Traffic Speed | DiDiJiNan \u003Cbr> DiDiXiAn | HGCN | [Hierarchical Graph Convolution Network for Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16088) | [Code](https:\u002F\u002Fgithub.com\u002Fguokan987\u002FHGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fguokan987\u002FHGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fguokan987\u002FHGCN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | ETT \u003Cbr> Weather \u003Cbr> Electricity | Informer | [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17325) | [Code](https:\u002F\u002Fgithub.com\u002Fzhouhaoyi\u002FInformer2020) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhouhaoyi\u002FInformer2020?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhouhaoyi\u002FInformer2020?color=critical&style=social) | AAAI\u003Cbr>2021\n| Traffic Flow | NYCMetro \u003Cbr> NYC Bike \u003Cbr> NYC Taxi | MOTHER | [Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16603) | None | AAAI\u003Cbr>2021\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07(M) \u003Cbr> PEMS07(L) \u003Cbr> PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STFGNN | [Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16542) | [Mxnet](https:\u002F\u002Fgithub.com\u002FMengzhangLI\u002FSTFGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMengzhangLI\u002FSTFGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMengzhangLI\u002FSTFGNN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | BJ Taxi \u003Cbr> NYC Taxi \u003Cbr> NYC Bike1 \u003Cbr> NYC Bike2 | STGDN | [Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17761) | [Mxnet](https:\u002F\u002Fgithub.com\u002Fnimingniming\u002Fgdn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnimingniming\u002Fgdn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnimingniming\u002Fgdn?color=critical&style=social) | AAAI\u003Cbr>2021\n| Traffic Flow | SG-TAXI | TrGNN | [Traffic Flow Prediction with Vehicle Trajectories](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16104) | [Code](https:\u002F\u002Fgithub.com\u002Fmingqian000\u002FTrGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmingqian000\u002FTrGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmingqian000\u002FTrGNN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Multivariat | Road \u003Cbr> POIs \u003Cbr> SIGtraf | DMLM | [Predicting Traffic Congestion Evolution: A Deep Meta Learning Approach](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0417.pdf) | [Future](https:\u002F\u002Fgithub.com\u002FHelenaYD\u002FDMLM) | IJCAI\u003Cbr>2021\n| Multivariat | East Bay \u003Cbr> METR-LA \u003Cbr> US | D-DA-GRNN | [EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458855) | [Code](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002FEnhanceNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frazvanc92\u002FEnhanceNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frazvanc92\u002FEnhanceNet?color=critical&style=social) | ICDE 2021\n| Multivariat | Water \u003Cbr> Humidity \u003Cbr> Wind, etc | EA-DRL | [An Actor-Critic Ensemble Aggregation Model for Time-Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458798) | None | ICDE 2021\n| Traffic Flow | TaxiBJ \u003Cbr> DiDiCD \u003Cbr> TaxiRome | AttConvLSTM | [Modeling Citywide Crowd Flows using Attentive Convolutional LSTM](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458664) | None | ICDE 2021\n| Traffic Speed \u003Cbr> Traffic Flow | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> eMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08...| Benchmark | [An Empirical Experiment on Deep Learning Models for Predicting Traffic Data](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458663) | [Future](https:\u002F\u002Fgithub.com\u002FHyunWookL\u002FAn-Empirical-Experiment-on-Deep-Learning-Models-for-Predicting-Traffic-Data) | ICDE 2021\n| Multivariat | Motes \u003Cbr> Soil \u003Cbr> Revenue \u003Cbr> Traffic \u003Cbr> 20CR | NET | [Network of Tensor Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3449969) | [Code](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FNET3) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbaoyujing\u002FNET3?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbaoyujing\u002FNET3?color=critical&style=social) | WWW 2021\n| Multivariat | VevoMusic \u003Cbr> WikiTraffic \u003Cbr> LOS-LOOP \u003Cbr> SZ-taxi | Radflow | [Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3449945) | [Code](https:\u002F\u002Fgithub.com\u002Falasdairtran\u002Fradflow) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falasdairtran\u002Fradflow?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falasdairtran\u002Fradflow?color=critical&style=social) | WWW 2021\n| Multivariat | METR-LA \u003Cbr> Wiki-EN | REST | [REST: Reciprocal Framework for Spatiotemporal-coupled Predictions](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3449928) | None | WWW 2021\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> HZMetro | ASTGNN | [Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9346058) | [Code](https:\u002F\u002Fgithub.com\u002FguoshnBJTU\u002FASTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FguoshnBJTU\u002FASTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FguoshnBJTU\u002FASTGNN?color=critical&style=social) | TKDE 2021\n| Multivariat | TaxiBJ \u003Cbr> BikeNYC-I \u003Cbr> BikeNYC-II \u003Cbr> TaxiNYC \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07(M) | DL-Traff | [DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482000) | Graph:[Code](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FDL-Traff-Graph) \u003Cbr> Grid:[TF](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FDL-Traff-Grid) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa20\u002FDL-Traff-Graph?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa20\u002FDL-Traff-Graph?color=critical&style=social) | CIKM\u003Cbr>2021\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07(M) | TorchGeoTem | [Code Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482000) | [Code](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002FCode_geometric_temporal) | CIKM\u003Cbr>2021\n| Traffic Flow | TaxiBJ \u003Cbr> BikeNYC | LLF | [Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482271) | None | CIKM\u003Cbr>2021\n| Multivariat | ETT \u003Cbr> Electricity | HI | [Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482120) | None | CIKM\u003Cbr>2021\n| Multivariat | ETT \u003Cbr> ELE | AGCNT | [AGCNT: Adaptive Graph Convolutional Network for Transformer-based Long Sequence Time-Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482054) | None | CIKM\u003Cbr>2021\n| Cellular Traffic | cellular | MPGAT | [Multivariate and Propagation Graph Attention Network for Spatial-Temporal Prediction with Outdoor Cellular Traffic](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482152) | [Code](https:\u002F\u002Fgithub.com\u002Fcylin-cmlab\u002FMPNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcylin-cmlab\u002FMPNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcylin-cmlab\u002FMPNet?color=critical&style=social) \u003Cbr> Future | CIKM\u003Cbr>2021\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> Simulated | STNN | [Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679008\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fsongyangco\u002FSTNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsongyangco\u002FSTNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsongyangco\u002FSTNN?color=critical&style=social) | ICDM 2021\n| Traffic Speed | DiDiCD \u003Cbr> DiDiXiAn | T-wave | [Trajectory WaveNet: A Trajectory-Based Model for Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679147) | [Code](https:\u002F\u002Fgithub.com\u002Fsongyangco\u002FSTNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsongyangco\u002FSTNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsongyangco\u002FSTNN?color=critical&style=social) | ICDM 2021\n| Multivariat | Sanyo \u003Cbr> Hanergy \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Exchange | SSDNet | [SSDNet: State Space Decomposition Neural Network for Time Series Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679135\u002F) | [Code](https:\u002F\u002Fgithub.com\u002FYangLIN1997\u002FSSDNet-ICDM2021) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYangLIN1997\u002FSSDNet-ICDM2021?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYangLIN1997\u002FSSDNet-ICDM2021?color=critical&style=social) | ICDM 2021\n| Traffic Volumn | HangZhou City \u003Cbr> JiNan City | CTVI | [Temporal Multi-view Graph Convolutional Networks for Citywide Traffic Volume Inference](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679045\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fdsj96\u002FCTVI-master) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdsj96\u002FCTVI-master?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdsj96\u002FCTVI-master?color=critical&style=social) | ICDM 2021\n| Traffic Volumn | Uber Movements \u003Cbr> Grab-Posisi | TEST-GCN | [TEST-GCN: Topologically Enhanced Spatial-Temporal Graph Convolutional Networks for Traffic Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679077) | None | ICDM 2021\n| Multivariat | Air Quality City \u003Cbr> Meterology | ATGCN | [Modeling Inter-station Relationships with Attentive Temporal Graph Convolutional Network for Air Quality Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441731) | None | WSDM 2021\n| Traffic Flow | WalkWLA \u003Cbr> BikeNYC \u003Cbr> TaxiNYC | PDSTN | [Predicting Crowd Flows via Pyramid Dilated Deeper Spatial-temporal Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441785) | None | WSDM 2021\n| Traffic Flow | PEMS04 \u003Cbr> PEMS08 | AGCRN | [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fce1aad92b939420fc17005e5461e6f48-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002FLeiBAI\u002FAGCRN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLeiBAI\u002FAGCRN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLeiBAI\u002FAGCRN?color=critical&style=social) | NeurIPS 2020\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> Wind \u003Cbr> Solar \u003Cbr> M4-Hourly | AST | [Adversarial Sparse Transformer for Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fc6b8c8d762da15fa8dbbdfb6baf9e260-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhihihihiwsf\u002FAST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhihihihiwsf\u002FAST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhihihihiwsf\u002FAST?color=critical&style=social) | NeurIPS 2020\n| Multivariat | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS07 \u003Cbr> PEMS03 \u003Cbr> PEMS04 ,etc | StemGNN | [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fcdf6581cb7aca4b7e19ef136c6e601a5-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FStemGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmicrosoft\u002FStemGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmicrosoft\u002FStemGNN?color=critical&style=social) | NeurIPS 2020\n| Multivariat | M4 \u003Cbr> M3 \u003Cbr> Tourism | N-BEATS | [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1ecqn4YwB) | [Code+Keras](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002Fn-beats) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fphilipperemy\u002Fn-beats?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fphilipperemy\u002Fn-beats?color=critical&style=social) | ICLR\u003Cbr>2020\n| Traffic Flow | Traffic \u003Cbr> Energy \u003Cbr> Electricity \u003Cbr> Exchange \u003Cbr> METR-LA \u003Cbr> PEMS-BAY | MTGNN | [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403118) | [Code](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FMTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnnzhan\u002FMTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnnzhan\u002FMTGNN?color=critical&style=social) | KDD\u003Cbr>2020\n| Traffic Flow | Taxi-NYC \u003Cbr> Bike-NYC \u003Cbr> CTM | DSAN | [Preserving Dynamic Attention for Long-Term Spatial-Temporal Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403118) | [TF](https:\u002F\u002Fgithub.com\u002Fhaoxingl\u002FDSAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhaoxingl\u002FDSAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhaoxingl\u002FDSAN?color=critical&style=social) | KDD\u003Cbr>2020\n| Traffic Speed \u003Cbr> Traffic Flow | Shenzhen | Curb-GAN | [Curb-GAN: Conditional Urban Traffic Estimation through Spatio-Temporal Generative Adversarial Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403127) | [Code](https:\u002F\u002Fgithub.com\u002FCurb-GAN\u002FCurb-GAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCurb-GAN\u002FCurb-GAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCurb-GAN\u002FCurb-GAN?color=critical&style=social) | KDD\u003Cbr>2020\n| Traffic Flow | TaxiBJ \u003Cbr> CrowdBJ \u003Cbr> TaxiJN \u003Cbr> TaxiGY | AutoST | [AutoST: Efficient Neural Architecture Search for Spatio-Temporal Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403122) | None | KDD\u003Cbr>2020\n| Traffic Volumn | W3-715 \u003Cbr> E5-2907 | HSTGCN | [Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403358) | None | KDD\u003Cbr>2020\n| Multivariat| Xiamen \u003Cbr> PEMS-BAY | GMAN | [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5477) | [TF](https:\u002F\u002Fgithub.com\u002Fzhengchuanpan\u002FGMAN)\u003Cbr> \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhengchuanpan\u002FGMAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhengchuanpan\u002FGMAN?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002FVincLee8188\u002FGMAN-Code) | AAAI\u003Cbr>2020\n| Multivariat | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | STSGCN | [Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5438) | [Mxnet](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FSTSGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDavidham3\u002FSTSGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDavidham3\u002FSTSGCN?color=critical&style=social) \u003Cbr> [Code](https:\u002F\u002Fgithub.com\u002FSmallNana\u002FSTSGCN_Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSmallNana\u002FSTSGCN_Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSmallNana\u002FSTSGCN_Code?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | Traffic \u003Cbr> Energy \u003Cbr> NASDAQ | MLCNN | [Towards Better Forecasting by Fusing Near and Distant Future Visions](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5466) | [Code](https:\u002F\u002Fgithub.com\u002FsmallGum\u002FMLCNN-Multivariate-Time-Series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FsmallGum\u002FMLCNN-Multivariate-Time-Series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FsmallGum\u002FMLCNN-Multivariate-Time-Series?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | PEMS-S \u003Cbr> PEMS-BAY \u003Cbr> METR-LA \u003Cbr> BJF \u003Cbr> BRF \u003Cbr> BRF-L | SLCNN | [Spatio-temporal graph structure learning for traffic forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5770) | None | AAAI\u003Cbr>2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | MRA-BGCN | [Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5758) | None | AAAI\u003Cbr>2020\n| Metro Flow | HKMetro | WDGTC | [Tensor Completion for Weakly-Dependent Data on Graph for Metro Passenger Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5915) | [TF](https:\u002F\u002Fgithub.com\u002Fbonaldli\u002FWDG_TC) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbonaldli\u002FWDG_TC?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbonaldli\u002FWDG_TC?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | MovingMNIST \u003Cbr> TaxiBJ \u003Cbr> KTH | SA-ConvLSTM | [Self-Attention ConvLSTM for Spatiotemporal Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6819) | [TF](https:\u002F\u002Fgithub.com\u002FMahatmaSun1\u002FSaConvSLTM) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMahatmaSun1\u002FSaConvSLTM?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMahatmaSun1\u002FSaConvSLTM?color=critical&style=social) \u003Cbr> [Code](https:\u002F\u002Fgithub.com\u002Fjerrywn121\u002FTianChi_AIEarth) | AAAI\u003Cbr>2020\n| Metro Flow | SydneyMetro | MLC-PPF | [Potential Passenger Flow Prediction-A Novel Study for Urban Transportation Development](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5819) | None | AAAI\u003Cbr>2020\n| Commuting Flow | Lodes \u003Cbr> Pluto \u003Cbr> OSRM | GMEL | [Learning Geo-Contextual Embeddings for Commuting Flow Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5425) | [Code](https:\u002F\u002Fgithub.com\u002Fjackmiemie\u002FGMEL) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjackmiemie\u002FGMEL?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjackmiemie\u002FGMEL?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | Traffic \u003Cbr> Exchange \u003Cbr> Solar | DeepTrends | [Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5496) | [TF](https:\u002F\u002Fgithub.com\u002FDerronXu\u002FDeepTrends) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDerronXu\u002FDeepTrends?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDerronXu\u002FDeepTrends?color=critical&style=social) | AAAI\u003Cbr>2020\n| Multivariat | Traffic \u003Cbr> Electricity \u003Cbr> SmokeVideo \u003Cbr> PCSales \u003Cbr> RawMaterials | BHT | [Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6032) | [Python](https:\u002F\u002Fgithub.com\u002Fhuawei-noah\u002FBHT-ARIMA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuawei-noah\u002FBHT-ARIMA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuawei-noah\u002FBHT-ARIMA?color=critical&style=social) | AAAI\u003Cbr>2020\n| Traffic Speed | PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | LSGCN | [LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.5555\u002F3491440.3491766) | [TF](https:\u002F\u002Fgithub.com\u002Fhelanzhu\u002FLSGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhelanzhu\u002FLSGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhelanzhu\u002FLSGCN?color=critical&style=social) | IJCAI\u003Cbr>2020\n| Traffic Flow | BikeNYC \u003Cbr> MobileBJ | CSCNet | [A Sequential Convolution Network for Population Flow Prediction with Explicitly Correlation Modelling](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.5555\u002F3491440.3491625) | None | IJCAI\u003Cbr>2020\n| Multivariat | USDCNY \u003Cbr> USDKRW \u003Cbr> USDIDR | WATTNet | [WATTNet: learning to trade FX via hierarchical spatio-temporal representation of highly multivariate time series](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0630.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Fpablovicente\u002Fkeras-wattnet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpablovicente\u002Fkeras-wattnet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpablovicente\u002Fkeras-wattnet?color=critical&style=social) | IJCAI\u003Cbr>2020\n| Fine-grained | CitiBikeNYC \u003Cbr> Div \u003Cbr> Metro | GACNN | [Towards Fine-grained Flow Forecasting: A Graph Attention Approach for Bike Sharing Systems](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380097) | None | WWW 2020\n| Flow \u003Cbr> Distribution | Austin \u003Cbr> Louisville \u003Cbr> Minneapolis | GCScoot | [Dynamic Flow Distribution Prediction for Urban Dockless E-Scooter Sharing Reconfiguration](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380101) | None | WWW 2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | STGNN | [Traffic Flow Prediction via Spatial Temporal Graph Neural Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380186) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FSTGNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FSTGNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FSTGNN?color=critical&style=social) | WWW 2020\n| Traffic Speed | DiDiCD | STAG-GCN | [Spatiotemporal Adaptive Gated Graph Convolution Network for Urban Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411894) | [Code](https:\u002F\u002Fgithub.com\u002FRobinLu1209\u002FSTAG-GCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRobinLu1209\u002FSTAG-GCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRobinLu1209\u002FSTAG-GCN?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | ST-GRAT | [ST-GRAT: A Novel Spatio-temporal Graph Attention Networks for Accurately Forecasting Dynamically Changing Road Speed](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411940) | [Code](https:\u002F\u002Fgithub.com\u002FLMissher\u002FST-GRAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMissher\u002FST-GRAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMissher\u002FST-GRAT?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Flow | BJ-Taxi \u003Cbr> NYC-Taxi \u003Cbr> NYC-Bike-1 \u003Cbr> NYC-Bike-2 | ST-CGA | [Spatial-Temporal Convolutional Graph Attention Networks for Citywide Traffic Flow Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411941) | [Keras](https:\u002F\u002Fgithub.com\u002Fjbdj-star\u002Fcga) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjbdj-star\u002Fcga?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjbdj-star\u002Fcga?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Flow | NYCBike \u003Cbr> NYCTaxi | MT-ASTN | [Multi-task Adversarial Spatial-Temporal Networks for Crowd Flow Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3412054) | [Code](https:\u002F\u002Fgithub.com\u002FMiaoHaoSunny\u002FMT-ASTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMiaoHaoSunny\u002FMT-ASTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FMiaoHaoSunny\u002FMT-ASTN?color=critical&style=social) | CIKM\u003Cbr>2020\n| Traffic Speed | SFO \u003Cbr> NYC | DIGC | [Deep Graph Convolutional Networks for Incident-Driven Traffic Speed Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411873) | None | CIKM\u003Cbr>2020\n| Metro Flow | SZMetro \u003Cbr> HZMetro | STP-TrellisNets | [STP-TrellisNets: Spatial-Temporal Parallel TrellisNets for Metro Station Passenger Flow Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411874) | None | CIKM\u003Cbr>2020\n| Multivariat | Air Quality \u003Cbr> BikeNYC \u003Cbr> METR-LA | AGSTN | [AGSTN: Learning Attention-adjusted Graph Spatio-Temporal Networks for Short-term Urban Sensor Value Forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338255) | [Keras](https:\u002F\u002Fgithub.com\u002Fl852888\u002FAGSTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fl852888\u002FAGSTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fl852888\u002FAGSTN?color=critical&style=social) | ICDM 2020\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | FreqST | [FreqST: Exploiting Frequency Information in Spatiotemporal Modeling for Traffic Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338305) | None | ICDM 2020\n| Traffic Flow | PEMS03 \u003Cbr> PEMS07 | TSSRGCN | [Tssrgcn: Temporal spectral spatial retrieval graph convolutional network for traffic flow forecasting](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338393) | None | ICDM 2020\n| Multivariat | Air Quality \u003Cbr> DarkSky \u003Cbr> Geographic | DeepLATTE | [Building Autocorrelation-Aware Representations for Fine-Scale Spatiotemporal Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338402) | [Code](https:\u002F\u002Fgithub.com\u002Fspatial-computing\u002Fdeeplatte-fine-scale-prediction) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspatial-computing\u002Fdeeplatte-fine-scale-prediction?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fspatial-computing\u002Fdeeplatte-fine-scale-prediction?color=critical&style=social) | ICDM 2020\n| Traffic Flow | XATaxi \u003Cbr> BJTaxi \u003Cbr> PortoTaxi | ST-PEFs | [Interpretable Spatiotemporal Deep Learning Model for Traffic Flow Prediction Based on Potential Energy Fields](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338315) | None | ICDM 2020\n| Traffic Speed \u003Cbr> Flow | SZSpeed \u003Cbr> SZTaxi | cST-ML | [cST-ML: Continuous Spatial-Temporal Meta-Learning for Traffic Dynamics Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338315) | [Code](https:\u002F\u002Fgithub.com\u002Fyingxue-zhang\u002FcST-ML) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyingxue-zhang\u002FcST-ML?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyingxue-zhang\u002FcST-ML?color=critical&style=social) | ICDM 2020\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> PEMS07(M) | DeepGLO | [Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F3a0844cee4fcf57de0c71e9ad3035478-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Frajatsen91\u002Fdeepglo) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frajatsen91\u002Fdeepglo?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Frajatsen91\u002Fdeepglo?color=critical&style=social) | NeurIPS 2019\n| Multivariat | Electricity \u003Cbr> Traffic \u003Cbr> Solar \u003Cbr> M4 \u003Cbr> Wind | LogSparse | [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F6775a0635c302542da2c32aa19d86be0-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fmlpotter\u002FTransformer_Time_Series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmlpotter\u002FTransformer_Time_Series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmlpotter\u002FTransformer_Time_Series?color=critical&style=social) | NeurIPS 2019\n| Multivariat | Synthetic \u003Cbr> ECG5000 \u003Cbr> Traffic | DILATE | [Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F466accbac9a66b805ba50e42ad715740-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fvincent-leguen\u002FDILATE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvincent-leguen\u002FDILATE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvincent-leguen\u002FDILATE?color=critical&style=social) | NeurIPS 2019\n| Traffic Flow | Earthquake | DeepUrbanEvent | [DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330996) | [Keras](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa\u002FDeepUrbanEvent) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdeepkashiwa\u002FDeepUrbanEvent?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdeepkashiwa\u002FDeepUrbanEvent?color=critical&style=social) | KDD\u003Cbr>2019\n| Traffic Flow \u003Cbr> Speed | TDrive \u003Cbr> METR-LA | ST-MetaNet | [Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330884) | [Mxnet](https:\u002F\u002Fgithub.com\u002Fpanzheyi\u002FST-MetaNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpanzheyi\u002FST-MetaNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpanzheyi\u002FST-MetaNet?color=critical&style=social) | KDD\u003Cbr>2019\n| Multivariat | Rossman \u003Cbr> Walmart \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Parts | ARU | [Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330996) | [TF](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002FARU) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpratham16cse\u002FARU?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpratham16cse\u002FARU?color=critical&style=social) | KDD\u003Cbr>2019\n| Multivariat | Air Quality | AccuAir | [AccuAir: Winning Solution to Air Quality Prediction for KDD Cup 2018](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330787) | None | KDD\u003Cbr>2019\n| Traffic Flow | Simulated \u003Cbr> RoadTraffic \u003Cbr> Wikipedia | ERMreg | [Regularized Regression for Hierarchical Forecasting Without Unbiasedness Conditions](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330976) | None | KDD\u003Cbr>2019\n| Multivariat \u003Cbr> under event | Climate \u003Cbr> Stock \u003Cbr> Pseudo | EVL | [Modeling Extreme Events in Time Series Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330896) |None | KDD\u003Cbr>2019\n| Traffic Flow | PEMS04 \u003Cbr> PEMS08 \u003Cbr> METR-LA | ASTGCN | [Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3881) | [Mxnet](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FASTGCN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDavidham3\u002FASTGCN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDavidham3\u002FASTGCN?color=critical&style=social) | AAAI\u003Cbr>2019\n| Traffic Flow \u003Cbr> Speed | NYC \u003Cbr> PEMS0(M) | DGCNN | [Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3877) | None | AAAI\u003Cbr>2019\n| Traffic FLow | NYC-Taxi \u003Cbr> NYC-Bike | STDN | [Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4511) | [Keras](https:\u002F\u002Fgithub.com\u002Ftangxianfeng\u002FSTDN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftangxianfeng\u002FSTDN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftangxianfeng\u002FSTDN?color=critical&style=social) | AAAI\u003Cbr>2019\n| Traffic Flow | MobileBJ \u003Cbr> BikeNYC | DeepSTN+ | [DeepSTN+: context-aware spatial-temporal neural network for crowd flow prediction in metropolis](https:\u002F\u002Fdoi.org\u002F10.1609\u002Faaai.v33i01.33011020) | [TF](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FDeepSTN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FDeepSTN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FDeepSTN?color=critical&style=social) | AAAI\u003Cbr>2019\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | Res-RGNN | [Gated residual recurrent graph neural networks for traffic prediction](https:\u002F\u002Fdoi.org\u002F10.1609\u002Faaai.v33i01.3301485) | None | AAAI\u003Cbr>2019\n| Traffic FLow | MetroBJ \u003Cbr> BusBJ \u003Cbr> TaxiBJ | GSTNet | [GSTNet: Global Spatial-Temporal Network for Traffic Flow Prediction](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0317.pdf) | [Code](https:\u002F\u002Fgithub.com\u002FWoodSugar\u002FGSTNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FWoodSugar\u002FGSTNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FWoodSugar\u002FGSTNet?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | GWN | [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2019\u002F264) | [Code](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FGraph-WaveNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnnzhan\u002FGraph-WaveNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnnzhan\u002FGraph-WaveNet?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Traffic Flow | DidiSY \u003Cbr> BikeNYC \u003Cbr> TaxiBJ | STG2Seq | [STG2Seq: Spatial-Temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=Ein6fZbizNZ) | [TF](https:\u002F\u002Fgithub.com\u002FLeiBAI\u002FSTG2Seq) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLeiBAI\u002FSTG2Seq?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLeiBAI\u002FSTG2Seq?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Multivariat | GHL \u003Cbr> Electricity \u003Cbr>TEP | DyAt | [DyAt Nets: Dynamic Attention Networks for State Forecasting in Cyber-Physical Systems](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0441.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Fnmuralid1\u002FDynamicAttentionNetworks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Multivariat | Air Quality | MGED | [Multi-Group Encoder-Decoder Networks to Fuse Heterogeneous Data for Next-Day Air Quality Prediction](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0603.pdf) | None | IJCAI\u003Cbr>2019\n| Traffic Volumn | Chicago \u003Cbr> Boston | MetaST | [Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313577) | [TF](https:\u002F\u002Fgithub.com\u002Fhuaxiuyao\u002FMetaST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuaxiuyao\u002FMetaST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuaxiuyao\u002FMetaST?color=critical&style=social) | WWW 2019\n| TrafficPred \u003Cbr> imputation |GZSpeed \u003Cbr> HZMetro \u003Cbr> Seattle \u003Cbr> London | BTF | [Bayesian Temporal Factorization for Multidimensional Time Series Prediction](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9380704) | [Python](https:\u002F\u002Fgithub.com\u002Fnmuralid1\u002FDynamicAttentionNetworks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnmuralid1\u002FDynamicAttentionNetworks?color=critical&style=social) | TPAMI 2019\n| Multivariat | Gas Station | DSANet | [DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3358132) | [Code](https:\u002F\u002Fgithub.com\u002Fbighuang624\u002FDSANet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbighuang624\u002FDSANet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbighuang624\u002FDSANet?color=critical&style=social) | CIKM\u003Cbr>2019\n| Multivariat | Solar \u003Cbr> Traffic \u003Cbr> Exchange \u003Cbr> Electricity \u003Cbr> PEMS ,etc | Study | [Experimental Study of Multivariate Time Series Forecasting Models](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357826) | None | CIKM\u003Cbr>2019\n| Traffic Speed | DiDiCD \u003Cbr> DiDiXA | BTRAC | [Boosted Trajectory Calibration for Traffic State Estimation](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970880) | None | ICDM 2019\n| Multivariat | Photovoltaic | MTEX-CNN | [MTEX-CNN: Multivariate Time Series EXplanations for Predictions with Convolutional Neural Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970899) | [Code](https:\u002F\u002Fgithub.com\u002Fduyanhpham-brs\u002FXAI-Multivariate-Time-Series) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fduyanhpham-brs\u002FXAI-Multivariate-Time-Series?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fduyanhpham-brs\u002FXAI-Multivariate-Time-Series?color=critical&style=social) | ICDM 2019\n| Traffic Speed | BJER4 \u003Cbr> PEMS07(M) \u003Cbr> PEMS07(L) | STGCN | [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=SkNeyVzOWB) | [TF](https:\u002F\u002Fgithub.com\u002FVeritasYin\u002FSTGCN_IJCAI-18) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVeritasYin\u002FSTGCN_IJCAI-18?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVeritasYin\u002FSTGCN_IJCAI-18?color=critical&style=social) [Mxnet](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FSTGCN) [Code1](https:\u002F\u002Fgithub.com\u002FFelixOpolka\u002FSTGCN-Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFelixOpolka\u002FSTGCN-Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFelixOpolka\u002FSTGCN-Code?color=critical&style=social) [Code2](https:\u002F\u002Fgithub.com\u002Fhazdzz\u002FSTGCN) [Code3](https:\u002F\u002Fgithub.com\u002FAguin\u002FSTGCN-Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAguin\u002FSTGCN-Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAguin\u002FSTGCN-Code?color=critical&style=social) | IJCAI\u003Cbr>2018\n| Traffic Speed | METR-LA \u003Cbr> PEMS-BAY | DCRNN | [Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting](https:\u002F\u002Fopenreview.net\u002Fforum?id=SJiHXGWAZ) | [TF](https:\u002F\u002Fgithub.com\u002Fliyaguang\u002FDCRNN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliyaguang\u002FDCRNN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliyaguang\u002FDCRNN?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002Fchnsh\u002FDCRNN_Code) |ICLR\u003Cbr>2018\n\n\n\n# [多变量概率时间序列预测](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表 |\n| :-: | :-: | :-: | :-: | :-: | - |\n| 论文数量：40+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| 概率 | 交易所 \u003Cbr> ILI \u003Cbr> ETT \u003Cbr> 电力 \u003Cbr> 交通 \u003Cbr> 天气 | TMDM | [用于概率多变量时间序列预测的Transformer调制扩散模型](https:\u002F\u002Fopenreview.net\u002Fforum?id=qae04YACHs) | 无 | ICLR\u003Cbr>2024\n| 概率 | 交易所 \u003Cbr> 太阳能 \u003Cbr> 电力 \u003Cbr> 交通 \u003Cbr> 出租车 \u003Cbr> Wikipedia | VQ-TR | [VQ-TR：用于时间序列预测的向量量化注意力](https:\u002F\u002Fopenreview.net\u002Fforum?id=IxpTsFS7mh) | 无 | ICLR\u003Cbr>2024\n| Conformer | COVID-19 | CopulaCPTS | [用于多步时间序列预测的Copula同形预测](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch54) | [代码](hhttps:\u002F\u002Fgithub.com\u002FRose-STL-Lab\u002FCopulaCPTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRose-STL-Lab\u002FCopulaCPTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRose-STL-Lab\u002FCopulaCPTS?color=critical&style=social) | ICLR\u003Cbr>2024 \n| 概率 | 太阳能 \u003Cbr> 电力 \u003Cbr> 交通 \u003Cbr> 出租车 \u003Cbr> Wikipedia | LDT | [用于概率时间序列预测的潜在扩散Transformer](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29085) | 无 | AAAI\u003Cbr>2024\n| 概率 | 太阳能 \u003Cbr> 电力 \u003Cbr> 交通 \u003Cbr> 交易所 \u003Cbr> M4-小时级 \u003Cbr> UberTLC \u003Cbr> KDDCup \u003Cbr> Wikipedia | TSDiff | [预测、精炼、合成：用于概率时间序列预测的自引导扩散模型](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F5a1a10c2c2c9b9af1514687bc24b8f3d-Abstract-Conference.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Famazon-science\u002Funconditional-time-series-diffusion) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famazon-science\u002Funconditional-time-series-diffusion?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famazon-science\u002Funconditional-time-series-diffusion?color=critical&style=social) | NIPS\u003Cbr>2023\n| 分位数 | 电力 \u003Cbr> Kaggle \u003Cbr> M4-每日 \u003Cbr> 交通 \u003Cbr> Wiki | Ensemble | [学习集成策略的理论保证及其在时间序列预测中的应用](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fhasson23a.html) | 无 | ICML\u003Cbr>2023\n| 分位数 | Boston \u003Cbr> Concrete \u003Cbr> kin8nm \u003Cbr> Power \u003Cbr> Protein \u003Cbr> Wine \u003Cbr> M5 | BVAE | [用于分位数概率建模的神经样条搜索](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26184) | 无 | AAAI\u003Cbr>2023\n| 分位数 | Traffc \u003Cbr> Electricity \u003Cbr> Solar Energy | pTSE | [pTSE：一种用于概率时间序列预测的多模型集成方法](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F521) | 无| IJCAI\u003Cbr>2023 \n| 概率 | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 | DeepSTUQ | [交通预测中的不确定性量化：一种统一的方法](https:\u002F\u002Fdoi.org\u002F10.1109\u002FICDE55515.2023.00081) | 无| ICDE 2023 \n| 概率 | Electricity \u003Cbr> Traffc \u003Cbr> Solar \u003Cbr> Exchange \u003Cbr> M4 | PDTrans | [用于时间序列预测的概率分解Transformer](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch54) | [代码](hhttps:\u002F\u002Fgithub.com\u002FJL-tong\u002FPDTrans) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJL-tong\u002FPDTrans?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJL-tong\u002FPDTrans?color=critical&style=social) | SDM 2023 \n| 概率 | Taxi\u003Cbr> \u003Cbr> Electricity Traffc\u003Cbr> Exchange | COPDEEPAR | [时序层次结构的一致性概率预测](https:\u002F\u002Fproceedings.mlr.press\u002Fv206\u002Frangapuram23a.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluonts\u002Ftree\u002Fdev\u002Fsrc\u002Fgluonts\u002Fnursery\u002Ftemporal_hierarchical_forecasting\u002Fmodel) | AISTATS 2023 \n| 概率 | Traffic \u003Cbr> Electricity \u003Cbr> Weather \u003Cbr> ETT \u003Cbr> Wind | BVAE | [使用扩散、去噪和解耦进行生成式时间序列预测](https:\u002F\u002Fopenreview.net\u002Fforum?id=rG0jm74xtx) | [Paddle](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FPaddleSpatial\u002Ftree\u002Fmain\u002Fresearch\u002FD3VAE) | NeurIPS 2022\n| 概率 & | Stock Price \u003Cbr> Wind Speed| Volat | [基于波动性的核函数和移动平均均值，用于高斯过程的精确预测](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fbenton22a.html) | [Code,GCode](https:\u002F\u002Fgithub.com\u002Fg-benton\u002FVolt) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fg-benton\u002FVolt?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fg-benton\u002FVolt?color=critical&style=social) | ICML\u003Cbr>2022\n| 概率 & Point & Others | electricity \u003Cbr> Yacht \u003Cbr> Boston, etc | AQF | [自回归分位数流用于预测性不确定性估计](https:\u002F\u002Fopenreview.net\u002Fforum?id=z1-I6rOKv1S) | 无 | ICLR\u003Cbr>2022\n| 概率 | IRIS \u003Cbr> Digits \u003Cbr> EightSchools | EMF | [嵌入式模型流：结合无模型深度学习与显式概率建模的归纳偏置](https:\u002F\u002Fopenreview.net\u002Fforum?id=9pEJSVfDbba) | [Code](https:\u002F\u002Fgithub.com\u002Fgisilvs\u002FEmbeddedModelFlows) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgisilvs\u002FEmbeddedModelFlows?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgisilvs\u002FEmbeddedModelFlows?color=critical&style=social) | ICLR\u003Cbr>2022\n| 概率 | Bike Sharing \u003Cbr> UCI \u003Cbr> NYU Depth v2 | NatPN | [自然后验网络：指数族分布的深度贝叶斯预测不确定性](https:\u002F\u002Fwww.in.tum.de\u002Fdaml\u002Fnatpn\u002F) | [Code](https:\u002F\u002Fgithub.com\u002Fborchero\u002Fnatural-posterior-network) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fborchero\u002Fnatural-posterior-network?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fborchero\u002Fnatural-posterior-network?color=critical&style=social) | ICLR\u003Cbr>2022\n| 概率 | Carbon \u003Cbr> Concrete \u003Cbr> Energy \u003Cbr> Housing,etc | β−NLL | [关于使用概率神经网络进行异方差不确定性估计的陷阱](https:\u002F\u002Fopenreview.net\u002Fforum?id=aPOpXlnV1T) | [Code](https:\u002F\u002Fgithub.com\u002Fmartius-lab\u002Fbeta-nll) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmartius-lab\u002Fbeta-nll?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmartius-lab\u002Fbeta-nll?color=critical&style=social) | ICLR\u003Cbr>2022\n| 概率 & Point | CDP \u003Cbr> SLD | STZINB-GNN | [利用时空图神经网络对稀疏出行需求预测进行不确定性量化](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539093) | [Code](https:\u002F\u002Fgithub.com\u002FZhuangDingyi\u002FSTZINB) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhuangDingyi\u002FSTZINB?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZhuangDingyi\u002FSTZINB?color=critical&style=social) | KDD\u003Cbr>2022\n| 概率 & Point | Sichuan \u003Cbr> Panama | PrEF | [PrEF：通过Copula增强的状态空间模型进行概率电力预测](https:\u002F\u002Faaai-2022虚拟椅子网上的海报aisi7128) | 无 | AAAI\u003Cbr>2022\n| 概率 | ETT \u003Cbr> Solar \u003Cbr> Electricity | KLST | [长 horizon 预测中的一致性概率聚合查询](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F404) | [Code](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002FAggForecaster) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpratham16cse\u002FAggForecaster?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpratham16cse\u002FAggForecaster?color=critical&style=social) | IJCAI\u003Cbr>2022\n| 概率 | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Wiki | EMSSM | [用于时间序列预测的记忆增强状态空间模型](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F479) | 无 | IJCAI\u003Cbr>2022\n| 预测区间 | DMV \u003Cbr> Census \u003Cbr> Forest \u003Cbr> Power | Evaluation | [针对学习到的基数估计的预测区间：一项实验评估](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F404) | 无 | ICDE 2022\n| 周期性预测 | ETT \u003Cbr> Weather | DeepFS | [将自注意力机制与时间序列分解相结合，用于周期性预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557077) | 无 | CIKM\u003Cbr>2022\n| 概率 | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> M4 | ISQF | [无需交叉分位数即可学习分位数函数，用于无分布假设的时间序列预测](https:\u002F\u002Fproceedings.mlr.press\u002Fv151\u002Fpark22a.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluonts\u002Fblob\u002F4fef7e26470d15096b11b005be846dedf87fb736\u002Fsrc\u002Fgluonts\u002Ftorch\u002Fdistributions\u002Fisqf.py) | AISTATS 2022\n| 概率 | M4 \u003Cbr> Traffic \u003Cbr> Electricity | Robust | [稳健的概率时间序列预测](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.11910) | [GluonTS](https:\u002F\u002Fgithub.com\u002Ftetrzim\u002Frobust-probabilistic-forecasting) | AISTATS 2022\n| 概率 | Electricity \u003Cbr> Traffic \u003Cbr> M4 | MQF | [多变量分位数函数预测器](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.11316.pdf) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluon-ts\u002Ftree\u002Fmaster\u002Fsrc\u002FGluonTS\u002Ftorch\u002Fmodel\u002Fmqf2) | AISTATS 2022\n| 概率 | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> Azure | C2FAR | [C2FAR：从粗到细的自回归网络，用于精确的概率预测](https:\u002F\u002Fopenreview.net\u002Fforum?id=lHuPdoHBxbg) | [Future](https:\u002F\u002Fgithub.com\u002Fhuaweicloud\u002Fc2far_forecasting) | AISTATS 2022\n| 插补 & 概率 | PhysioNet \u003Cbr> Air Quality | CSDI | [CSDI：用于概率时间序列插补的条件分数扩散模型](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fcfe8504bda37b575c70ee1a8276f3486-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fermongroup\u002FCSDI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fermongroup\u002FCSDI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fermongroup\u002FCSDI?color=critical&style=social) | NeurIPS 2021\n| 概率 | MIMIC-III \u003Cbr> EEG \u003Cbr> COVID-19 | CF-RNN | [同形时间序列预测](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F312f1ba2a72318edaaa995a67835fad5-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fkamilest\u002Fconformal-rnn) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkamilest\u002Fconformal-rnn?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkamilest\u002Fconformal-rnn?color=critical&style=social) | NeurIPS 2021\n| 概率 | CDC Flu | EPIFNP | [当存疑时：用于流行病预测的神经非参数不确定性量化](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fa4a1108bbcc329a70efa93d7bf060914-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FEpiFNP) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAdityaLab\u002FEpiFNP?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAdityaLab\u002FEpiFNP?color=critical&style=social) | NeurIPS 2021\n| 概率 | Basketball \u003Cbr> Weather| GLIM | [概率路径与随时间变化的预测结构](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F7f53f8c6c730af6aeb52e66eb74d8507-Abstract.html) | [R](https:\u002F\u002Fgithub.com\u002FItsMrLin\u002Fprobability-paths) | NeurIPS 2021\n| 概率 | Facebook \u003Cbr> Meps \u003Cbr> Star \u003Cbr> Bike ,etc | LSF | [概率预测：一种水平集方法](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F32b127307a606effdcc8e51f60a45922-Abstract.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluon-ts\u002Ftree\u002Fmaster\u002Fsrc\u002FGluonTS\u002Fmodel\u002Frotbaum) | NeurIPS 2021\n| 概率 | Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wikipedia | ProTran | [用于时间序列分析的概率Transformer](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fc68bd9055776bf38d8fc43c0ed283678-Abstract.html) | 无 | NeurIPS 2021\n| 预测区间 | Solar \u003Cbr> Wind | EnbPI | [动态时间序列的同形预测区间](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fxu21h.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhamrel-cxu\u002FEnbPI) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhamrel-cxu\u002FEnbPI?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhamrel-cxu\u002FEnbPI?color=critical&style=social) | ICML\u003Cbr>2021\n| 概率 | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wiki | TimeGrad | [用于多变量概率时间序列预测的自回归去噪扩散模型](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Frasul21a.html) | [Code](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002FCode-ts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) | ICML\u003Cbr>2021\n| 概率 & Point | PEMS03 \u003Cbr> PEMS04 \u003Cbr> PEMS07 \u003Cbr> PEMS08 \u003Cbr> Electricity \u003Cbr> Traffic , etc | AGCGRU | [带有粒子流的RNN，用于概率时空预测](https:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fpal21b.html) | [TF](https:\u002F\u002Fgithub.com\u002Fnetworkslab\u002Frnn_flow) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnetworkslab\u002Frnn_flow?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnetworkslab\u002Frnn_flow?color=critical&style=social) | ICML\u003Cbr>2021\n| 概率 | Tourism \u003Cbr> Labour \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> Electricity \u003Cbr> Traffic , etc | Hier-E2E | [用于层次化时间序列的一致性概率预测的端到端学习](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Frangapuram21a.html) | [MXNet](https:\u002F\u002Fgithub.com\u002Frshyamsundar\u002FGluonTS-hierarchical-ICML-2021) | ICML\u003Cbr>2021\n| 概率 | Sine \u003Cbr> MNIST \u003Cbr> Billiards \u003Cbr> S&P \u003Cbr> Stock | Whittle | [Whittle网络：一种用于时间序列的深度似然模型](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fyu21c.html) | [TF](https:\u002F\u002Fgithub.com\u002Fml-research\u002FWhittleNetworks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fml-research\u002FWhittleNetworks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fml-research\u002FWhittleNetworks?color=critical&style=social) | ICML\u003Cbr>2021\n| 概率 | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PMU | GTS | [用于预测多个时间序列的离散图结构学习](https:\u002F\u002Fopenreview.net\u002Fforum?id=WEHSlH5mOk) | [Code](https:\u002F\u002Fgithub.com\u002Fchaoshangcs\u002FGTS) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchaoshangcs\u002FGTS?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchaoshangcs\u002FGTS?color=critical&style=social) | ICLR\u003Cbr>2021\n| 概率 & Point| Exchange \u003Cbr>Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Taxi \u003Cbr> Wikipedia | MAF | [通过条件归一化流进行多变量概率时间序列预测](https:\u002F\u002Fopenreview.net\u002Fforum?id=WiGQBFuVRv) | [Code](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002FCode-ts) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzalandoresearch\u002FCode-ts?color=critical&style=social) | ICLR\u003Cbr>2021\n| 概率 | MNIST \u003Cbr> PhysioNet2012 | PNCNN | [概率数值卷积神经网络](https:\u002F\u002Fopenreview.net\u002Fforum?id=T1XmO8ScKim) | 无 | ICLR\u003Cbr>2021\n| 概率 & Point | Energy \u003Cbr> Wine \u003Cbr> Power \u003Cbr> MSD, etc | PGBM | [用于大规模概率回归的概率梯度提升机](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467278) | [Code](https:\u002F\u002Fgithub.com\u002Felephaint\u002Fpgbm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Felephaint\u002Fpgbm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Felephaint\u002Fpgbm?color=critical&style=social) | KDD\u003Cbr>2021\n| 概率 | DiDICD | TrajNet | [TrajNet：一种基于轨迹的深度学习模型，用于交通预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467236) | 无 | KDD\u003Cbr>2021\n| 概率 | Air Quality \u003Cbr> METR-LA \u003Cbr> COVID-19 | UQ | [量化深度时空预测中的不确定性](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467325) | [Code](https:\u002F\u002Fgithub.com\u002FDongxiaW\u002FQuantifying_Uncertainty_in_Deep_Spatiotemporal_Forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDongxiaW\u002FQuantifying_Uncertainty_in_Deep_Spatiotemporal_Forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDongxiaW\u002FQuantifying_Uncertainty_in_Deep_Spatiotemporal_Forecasting?color=critical&style=social) | KDD\u003Cbr>2021\n| 概率 | Electricity \u003Cbr> Traffic \u003Cbr> Environment \u003Cbr> Air Quality \u003Cbr> Dewpoint,etc| VSMHN | [为多horizon概率预测协同学习异质时间序列](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17023) | [Code](https:\u002F\u002Fgithub.com\u002Flongyuanli\u002FVSMHN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flongyuanli\u002FVSMHN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flongyuanli\u002FVSMHN?color=critical&style=social) | AAAI\u003Cbr>2021\n| 概率 & Point | Traffic \u003Cbr> Electricity \u003Cbr> Wiki \u003Cbr> Solar \u003Cbr> Taxi | TLAE | [时间潜伏自动编码器：一种用于概率多变量时间序列预测的方法](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17101) | 无 | AAAI\u003Cbr>2021\n| 概率 | Patient EHR \u003Cbr> Public Health | UNITE | [UNITE：基于不确定性的健康风险预测，利用多源数据](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450087) | [Code](https:\u002F\u002Fgithub.com\u002FChacha-Chen\u002FUNITE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChacha-Chen\u002FUNITE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FChacha-Chen\u002FUNITE?color=critical&style=social) | WWW 2021\n| 概率 | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> Wiki | ARSGLS | [用于时间序列预测的深度Rao-Blackwell化粒子滤波器](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fafb0b97df87090596ae7c503f60bb23f-Abstract.html) | 无 | NeurIPS 2020\n| 概率 | Electricity \u003Cbr> Traffic \u003Cbr> Wind \u003Cbr> Solar \u003Cbr> M4 | AST | [对抗性稀疏Transformer用于时间序列预测](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fc6b8c8d762da15fa8dbbdfb6baf9e260-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fhihihihiwsf\u002FAST) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhihihihiwsf\u002FAST?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhihihihiwsf\u002FAST?color=critical&style=social) | NeurIPS 2020\n| 概率 | Traffic \u003Cbr> Electricity | STRIPE | [具有形状和时间多样性的概率时间序列预测](https:\u002F\u002Fpapers.NeurIPS.cc\u002Fpaper\u002F2020\u002Fhash\u002F2f2b265625d76a6704b08093c652fd79-Abstract.html) | [Code](https:\u002F\u002Fgithub.com\u002Fvincent-leguen\u002FSTRIPE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvincent-leguen\u002FSTRIPE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvincent-leguen\u002FSTRIPE?color=critical&style=social) | NeurIPS 2020\n| 概率 | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Wiki \u003Cbr> Traffic | NKF | [用于多变量时间序列分析的归一化卡尔曼滤波器](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F1f47cef5e38c952f94c5d61726027439-Abstract.html) | 无 | NeurIPS 2020\n| 分位数 | MIMIC-III | BJRNN | [通过分块影响函数在RNN中实现频率论不确定性](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Falaa20b.html) | [Code](https:\u002F\u002Fgithub.com\u002Fahmedmalaa\u002Frnn-blockwise-jackknife) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fahmedmalaa\u002Frnn-blockwise-jackknife?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fahmedmalaa\u002Frnn-blockwise-jackknife?color=critical&style=social) | ICML\u003Cbr>2020\n| 概率 | S&P 500 \u003Cbr> Electricity | Monte-Carlo | [对抗性攻击对概率自回归预测模型的影响](https:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fdang-nhu20a.html) | [Code](https:\u002F\u002Fgithub.com\u002Feth-sri\u002Fprobabilistic-forecasts-attacks) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Feth-sri\u002Fprobabilistic-forecasts-attacks?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Feth-sri\u002Fprobabilistic-forecasts-attacks?color=critical&style=social) | ICML\u003Cbr>2020\n| 概率 | Boston \u003Cbr> Concrete \u003Cbr>Energy \u003Cbr> Kin8nm \u003Cbr> Naval, etc | NGBoost | [NGBoost：用于概率预测的自然梯度提升](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fduan20a.html) | [Python](https:\u002F\u002Fgithub.com\u002Fstanfordmlgroup\u002Fngboost) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fstanfordmlgroup\u002Fngboost?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fstanfordmlgroup\u002Fngboost?color=critical&style=social) | ICML\u003Cbr>2020\n| 概率 | Physionet \u003Cbr> NHIS | DME | [使用高斯过程的深度混合效应模型：一种个性化且可靠的医疗保健预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5773) | [Code](https:\u002F\u002Fgithub.com\u002Fjik0730\u002FDeep-Mixed-Effect-Model-using-Gaussian-Processes) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjik0730\u002FDeep-Mixed-Effect-Model-using-Gaussian-Processes?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjik0730\u002FDeep-Mixed-Effect-Model-using-Gaussian-Processes?color=critical&style=social) | AAAI\u003Cbr>2020\n| 概率 | Exchange \u003Cbr> Solar \u003Cbr> Electricity \u003Cbr> Traffic \u003Cbr> NYCTaxi \u003Cbr> Wikipedia | copula | [使用低秩高斯Copula过程进行高维多变量预测](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F0b105cf1504c4e241fcc6d519ea962fb-Abstract.html) | [GluonTS](https:\u002F\u002Fgithub.com\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release) | NeurIPS 2019\n| 概率 | Electricity \u003Cbr> Traffic \u003Cbr> NYCTaxi \u003Cbr> Uber | DF | [用于预测的深度因子](https:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fwang19k.html) | 无 | ICML\u003Cbr>2019\n| 概率 | Weather | DUQ | [深度不确定性量化：一种用于天气预报的机器学习方法](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330704) | [Keras](https:\u002F\u002Fgithub.com\u002FBruceBinBoxing\u002FDeep_Learning_Weather_Forecasting) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBruceBinBoxing\u002FDeep_Learning_Weather_Forecasting?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBruceBinBoxing\u002FDeep_Learning_Weather_Forecasting?color=critical&style=social) | KDD\u003Cbr>2019\n| 概率 | JD50K | framework | [利用时间注意力学习进行多horizon时间序列预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330662) | 无 | KDD\u003Cbr>2019\n| 概率 | MIMIC-III | TPF | [用于ICU脓毒症预测的时间概率特征](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330747) | 无 | KDD\u003Cbr>2019\n| 概率 | Electricity \u003Cbr> Traffic \u003Cbr> Wiki \u003Cbr> Dom | SQF | [使用样条分位数函数RNN进行概率预测](https:\u002F\u002Fproceedings.mlr.press\u002Fv89\u002Fgasthaus19a.html) | 无 | AISTATS 2019\n| 概率 | 更多 | More | [https:\u002F\u002Fgithub.com\u002Fzzw-zwzhang\u002FAwesome-of-Time-Series-Prediction](https:\u002F\u002Fgithub.com\u002Fzzw-zwzhang\u002FAwesome-of-Time-Series-Prediction) | 更多 |\n\n\u003C!--\n| 概率型 | 电力 \u003Cbr> 交通 \u003Cbr> 维基 \u003Cbr> Dom | SQF | [基于样条分位数函数RNN的概率预测](https:\u002F\u002Fproceedings.mlr.press\u002Fv89\u002Fgasthaus19a.html) | 无 | AISTATS 2019 \n\n| 概率型 | 电力 \u003Cbr> 交通 \u003Cbr> NYCTaxi \u003Cbr> Uber | 框架 | [基于时间注意力学习的多步时序预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330662) | [代码](https:\u002F\u002Fgithub.com\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmbohlkeschneider\u002Fgluon-ts\u002Ftree\u002Fmv_release?color=critical&style=social) | KDD\u003Cbr>2019 -->\n\n# [时间序列插补](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表 |\n| :-: | :-: | :-: | :-: | :-: | - |\n| 论文数量：30+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| ImputeFormer | METR-LA \u003Cbr> PEMS-BAY \u003Cbr> PEMS03478 \u003Cbr> Solar \u003Cbr> CER-EN \u003Cbr> AQI | ImputeFormer | [ImputeFormer: 低秩诱导的可泛化时空插补Transformer](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3637528.3671751) | [代码](https:\u002F\u002Fgithub.com\u002Ftongnie\u002FImputeFormer) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftongnie\u002FImputeFormer?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftongnie\u002FImputeFormer?color=critical&style=social) | KDD\u003Cbr>2024\n| 插补 | AirQuality \u003Cbr> Stocks \u003Cbr> Electricity \u003Cbr> Energy | CTA | [用于规则与不规则时间序列插补的连续时间自编码器](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fchen23f.html) | [代码](https:\u002F\u002Fgithub.com\u002Fhyowonwi\u002FCTA) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhyowonwi\u002FCTA?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhyowonwi\u002FCTA?color=critical&style=social) | WSDM 2024\n| 插补 | PM2.5 \u003Cbr> PhysioNet | CSBI | [具有概率保证收敛性的薛定谔桥及其在概率性时间序列插补中的应用](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fchen23f.html) | [代码](https:\u002F\u002Fgithub.com\u002Fmorganstanley\u002FMSML) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmorganstanley\u002FMSML?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmorganstanley\u002FMSML?color=critical&style=social) | ICML\u003Cbr>2023\n| 插补 | MIMIC-III \u003Cbr> PhysioNet | MNAR | [面向缺失数据的时间序列分类的概率性插补](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fkim23m.html) | [TF](https:\u002F\u002Fgithub.com\u002Fyuneg11\u002FSupNotMIWAE-with-ObsDropout) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyuneg11\u002FSupNotMIWAE-with-ObsDropout?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyuneg11\u002FSupNotMIWAE-with-ObsDropout?color=critical&style=social) | ICML\u003Cbr>2023\n| 插补 | Guangzhou \u003Cbr> Solar-energy\u003Cbr> Westminster | TIDER \u003Cbr>(EncDec,AR) | [基于解耦时序表示的多变量时间序列插补](https:\u002F\u002Fopenreview.net\u002Fforum?id=rdjeCNUS6TG) | [代码](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002FTIDER-527C\u002Freadme.md) | ICLR\u003Cbr>2023\n| 插补 | COVID-19 \u003Cbr> AQ36 \u003Cbr> PeMS-BA \u003Cbr> PeMS-LA \u003Cbr> PeMS-SD| PoGeVon | [基于位置感知图增强变分自编码器的网络化时间序列插补](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3580305.3599444) | [作者](https:\u002F\u002Fgithub.com\u002FDerek-Wds) | KDD\u003Cbr>2023\n| 插补 | PhysioNet \u003Cbr> Human Activity | Warpformer | [Warpformer: 面向不规则临床时间序列的多尺度建模方法](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599543) | [代码](https:\u002F\u002Fgithub.com\u002FimJiawen\u002FWarpformer) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FimJiawen\u002FWarpformer?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FimJiawen\u002FWarpformer?color=critical&style=social) | KDD\u003Cbr>2023\n| 插补 | Air Quality \u003Cbr> METR-LA\u003Cbr> PEMS-BAY | PriSTI | [PriSTI: 用于时空插补的条件扩散框架](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.09746) | [代码](https:\u002F\u002Fgithub.com\u002FLMZZML\u002FPriSTI) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLMZZML\u002FPriSTI?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLMZZML\u002FPriSTI?color=critical&style=social) | ICDE 2023\n| 插补 | PhysioNet12 \u003Cbr> PhysioNet19 \u003Cbr> MIMIC-III | DA-TASWDM | [面向医疗时间序列插补的密度感知时序注意力逐步扩散模型](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614840) | 无 | CIKM\u003Cbr>2023\n| 插补 | TEDDY \u003Cbr> CAMELS | TSEst | [基于注意力的高缺失率时间序列多模态缺失值插补](hhttps:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch53) | [代码](https:\u002F\u002Fgithub.com\u002Fcompbiolabucf\u002FTSEst) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcompbiolabucf\u002FTSEst?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcompbiolabucf\u002FTSEst?color=critical&style=social) | SDM 2023\n| 插补 | Air Quality \u003Cbr> METR-LA \u003Cbr> PEMS-BAY \u003Cbr> CER-E | GRIN \u003Cbr>(EncDec,AR) | [通过图神经网络填补多变量时间序列空缺](https:\u002F\u002Fopenreview.net\u002Fforum?id=kOu3-S3wJ7) | [代码](https:\u002F\u002Fgithub.com\u002FGraph-Machine-Learning-Group\u002Fgrin) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGraph-Machine-Learning-Group\u002Fgrin?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGraph-Machine-Learning-Group\u002Fgrin?color=critical&style=social) | ICLR\u003Cbr>2022\n| 插补 | PhysioNet \u003Cbr> MIMIC-III \u003Cbr> Climate | HeTVAE \u003Cbr>(Attn,VAE) | [异方差时序变分自编码器用于不规则采样时间序列](https:\u002F\u002Fopenreview.net\u002Fforum?id=Az7opqbQE-3) | [代码](https:\u002F\u002Fgithub.com\u002Freml-lab\u002Fhetvae) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Freml-lab\u002Fhetvae?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Freml-lab\u002Fhetvae?color=critical&style=social) | ICLR\u003Cbr>2022\n| 插补 | MIMIC-III \u003Cbr> OPHTHALMIC \u003Cbr> MNIST Physionet \u003Cbr> | GIL \u003Cbr>(AR,Attn, \u003Cbr> 梯度学习) | [针对不完全观测的梯度重要性学习](https:\u002F\u002Fopenreview.net\u002Fforum?id=fXHl76nO2AZ) | [TF](https:\u002F\u002Fgithub.com\u002Fgaoqitong\u002Fgradient-importance-learning) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgaoqitong\u002Fgradient-importance-learning?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgaoqitong\u002Fgradient-importance-learning?color=critical&style=social) | ICLR\u003Cbr>2022\n| 插补 | 氯浓度 \u003Cbr> SML2010 \u003Cbr> Air Quality | D-NLMC | [动态非线性矩阵补全用于时变数据插补](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai12088) | [Matlab](https:\u002F\u002Fgithub.com\u002Fjicongfan) \u003Cbr> 作者 \u003Cbr> Github | AAAI\u003Cbr>2022\n| 插补 | COMPAS \u003Cbr> Adult \u003Cbr> HSLS | ME | [基于高斯Copula的在线缺失值插补与变点检测](https:\u002F\u002Faaai-2022虚拟椅子网海报_aaai6237) | [gcimpute](https:\u002F\u002Fgithub.com\u002Fyuxuanzhao2295\u002FOnline-Missing-Value-Imputation-and-Change-Point-Detection-with-the-Gaussian-Copula) | AAAI\u003Cbr>2022\n| 插补 | 公平MIP森林 | | [无需插补的公平性：一种处理缺失值的决策树公平预测方法](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F21189) | 无 | AAAI\u003Cbr>2022\n| 插补 | Chengdu \u003Cbr> New York | STCPA | [基于时空注意力和周期感知训练的交通速度插补](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557480) | [代码](https:\u002F\u002Fgithub.com\u002FSam1224\u002FSTCPA) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSam1224\u002FSTCPA?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSam1224\u002FSTCPA?color=critical&style=social) | CIKM\u003Cbr>2022\n| 插补 | Nanjingyby \u003Cbr> PEMS08 | AST-CMCN | [无生成式城市流量插补](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557334) | SenzhangWang | CIKM\u003Cbr>2022\n| 插补 | Foursquare \u003Cbr> Gowalla | MDI-MG | [用于缺失出行数据插补的多任务生成对抗网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557654) | 无 | CIKM\u003Cbr>2022\n| 插补 | 自定义 | MACRO | [用于细粒度车道级交通流量插补的多图卷积循环网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027759) | [代码](https:\u002F\u002Fgithub.com\u002FJingci\u002FMACRO) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJingci\u002FMACRO?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJingci\u002FMACRO?color=critical&style=social) | ICDM 2022\n| 插补 | Physionet \u003Cbr> MIMIC-III \u003Cbr> Human Activity | mTAND | [用于不规则采样时间序列的多时间注意力网络](https:\u002F\u002Fopenreview.net\u002Fforum?id=4c0J6lwQ4_) | [代码](https:\u002F\u002Fgithub.com\u002Freml-lab\u002FmTAN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Freml-lab\u002FmTAN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Freml-lab\u002FmTAN?color=critical&style=social) | ICLR\u003Cbr>2021\n| 插补 | METR-LA \u003Cbr> NREL \u003Cbr> USHCN \u003Cbr> SeData | IGNNK | [归纳式图神经网络用于时空克里金插补](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16575) | [代码](https:\u002F\u002Fgithub.com\u002FKaimaoge\u002FIGNNK) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKaimaoge\u002FIGNNK?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FKaimaoge\u002FIGNNK?color=critical&style=social) | AAAI\u003Cbr>2021\n| 插补 | Activity \u003Cbr> PhysioNet \u003Cbr> Air Quality | SSGAN | [用于多变量时间序列插补的生成式半监督学习](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17086) | [代码](https:\u002F\u002Fgithub.com\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation?color=critical&style=social) | AAAI\u003Cbr>2021\n| 插补 & 多变量 | PhysioNet \u003Cbr> Air Quality | CSDI | [CSDI: 基于分数的条件扩散模型用于概率性时间序列插补](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fcfe8504bda37b575c70ee1a8276f3486-Abstract.html) | [代码](https:\u002F\u002Fgithub.com\u002Fermongroup\u002FCSDI) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fermongroup\u002FCSDI?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fermongroup\u002FCSDI?color=critical&style=social) | NeurIPS 2021\n| 插补 & 预测 | VevoMusic \u003Cbr> WikiTraffic \u003Cbr> Los-Loop \u003Cbr> SZ-Taxi | Radflow | [Radflow: 一种用于时间序列网络的递归、聚合与分解模型](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3442381.3449945) | [代码](https:\u002F\u002Fgithub.com\u002Falasdairtran\u002Fradflow) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falasdairtran\u002Fradflow?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Falasdairtran\u002Fradflow?color=critical&style=social) | WWW 2021\n| 插补 | PhysioNet \u003Cbr> Air Quality \u003Cbr> Gas Sensor | STING | [STING: 基于自注意力的GAN驱动时间序列插补网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679183) | 无 | ICDM 2021\n| 插补 | Zero \u003Cbr> MICE \u003Cbr> SoftImpute \u003Cbr> GMMC \u003Cbr> GAIN | SN | [为何不应使用零值插补？纠正神经网络训练中的稀疏性偏差](https:\u002F\u002Fopenreview.net\u002Fforum?id=BylsKkHYvH) | [Future](https:\u002F\u002Fgithub.com\u002FJoonyoungYi\u002Fsparsity-normalization) | ICLR\u003Cbr>2020\n| 插补 | Beijing Air \u003Cbr> PhysioNet \u003Cbr> Porto Taxi \u003Cbr> London Weather | LGnet | [联合建模本地与全球时序动态，用于有缺失值的多变量时间序列预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6056) | 无 | AAAI\u003Cbr>2020\n| 插补 | Sydney \u003Cbr> Melbourne \u003Cbr> Brisbane \u003Cbr> Perth, etc | SMV-NMF | [一种用于多视角城市统计数据的空间缺失值插补方法](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0182.pdf) | [Matlab](https:\u002F\u002Fgithub.com\u002FSMV-NMF\u002FSMV-NMF) | IJCAI\u003Cbr>2020\n| 插补 | PhysioNet \u003Cbr> Air Quality \u003Cbr> Wind | GANGRUI | [对抗式递归时间序列插补](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9158560\u002F) | 无 | TNNLS 2020\n| 插补 | Healthcare \u003Cbr> Climate | GRU-ODE-Bayes | [GRU-ODE-Bayes: 连续建模偶发观测时间序列](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F455cb2657aaa59e32fad80cb0b65b9dc-Abstract.html) | [代码](https:\u002F\u002Fgithub.com\u002Fedebrouwer\u002Fgru_ode_bayes) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fedebrouwer\u002Fgru_ode_bayes?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fedebrouwer\u002Fgru_ode_bayes?color=critical&style=social) | NeurIPS 2019\n| 插补 | Toy | LatenODE | [用于不规则采样时间序列的潜在常微分方程](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F42a6845a557bef704ad8ac9cb4461d43-Abstract.html) | [代码](https:\u002F\u002Fgithub.com\u002FYuliaRubanova\u002Flatent_ode) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYuliaRubanova\u002Flatent_ode?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYuliaRubanova\u002Flatent_ode?color=critical&style=social) | NeurIPS 2019\n| 插补 | Sines \u003Cbr> Stocks\u003Cbr> Energy \u003Cbr> Events | TimeGAN | [时间序列生成对抗网络](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fc9efe5f26cd17ba6216bbe2a7d26d490-Abstract.html) | [TF](https:\u002F\u002Fgithub.com\u002Fjsyoon0823\u002FTimeGAN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjsyoon0823\u002FTimeGAN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fjsyoon0823\u002FTimeGAN?color=critical&style=social) | NeurIPS 2019\n| 插补 | MIMIC-III \u003Cbr> UWaveGesture | Inter-net | [用于不规则采样时间序列的插值-预测网络](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1efr3C9Ym) | [Keras](https:\u002F\u002Fgithub.com\u002Fmlds-lab\u002Finterp-net) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmlds-lab\u002Finterp-net?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmlds-lab\u002Finterp-net?color=critical&style=social) | ICLR\u003Cbr>2019\n| 插补 | PhysioNet \u003Cbr> KDD2018 | E2gan | [E2gan: 端到端生成对抗网络用于多变量时间序列插补](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0429.pdf) | [TF](https:\u002F\u002Fgithub.com\u002FLuoyonghong\u002FE2EGAN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLuoyonghong\u002FE2EGAN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLuoyonghong\u002FE2EGAN?color=critical&style=social) | IJCAI\u003Cbr>2019\n| 插补 | EC \u003Cbr> RV | STI | [你的邻居如何泄露你的信息：社交感知时间序列插补](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313714) | [代码](https:\u002F\u002Fgithub.com\u002Ftomstream\u002FSTI) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftomstream\u002FSTI?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftomstream\u002FSTI?color=critical&style=social) | WWW 2019\n\n\n\n# [Time Series Anomaly Detection](#content)\n| Task | Data | Model | Paper | Code | Publication |\n| :-: | :-: | :-: | :-: | :-: | - |\n| Paper Nums: 30+ | \u003Cimg width=90\u002F> | | | | \u003Cimg width=320\u002F> |\n| Anomaly Detection | Yahoo \u003Cbr> KPI \u003Cbr> WSD \u003Cbr> NAB | FCVAE | [Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3589334.3645710) | [Code](https:\u002F\u002Fgithub.com\u002FCSTCloudOps\u002FFCVAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCSTCloudOps\u002FFCVAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCSTCloudOps\u002FFCVAE?color=critical&style=social) | WWW 2024\n| Anomaly Detection | TODS \u003Cbr> ASD\u003Cbr> ECG \u003Cbr>PSM \u003Cbr> CompanyA | Dual-TF | [Breaking the Time-Frequency Granularity Discrepancy in Time-Series Anomaly Detection](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3589334.3645556) | [Code](https:\u002F\u002Fgithub.com\u002Fkaist-dmlab\u002FDualTF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkaist-dmlab\u002FDualTF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkaist-dmlab\u002FDualTF?color=critical&style=social) | WWW 2024\n| Anomaly Detection | SMD \u003Cbr> J-D1 \u003Cbr> J-D2 \u003Cbr>SMAP | LARA | [LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3589334.3645472) | None | WWW 2024\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> PSM \u003Cbr> SMD \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> Crediy \u003Cbr> Yahoo | | [When Model Meets New Normals: Test-Time Adaptation for Unsupervised Time-Series Anomaly Detection](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29210) | [Code](https:\u002F\u002Fgithub.com\u002FForestsKing\u002FD3R) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FForestsKing\u002FD3R?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FForestsKing\u002FD3R?color=critical&style=social) | AAAI\u003Cbr>2024\n| Anomaly Detection | SMD \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> SWaT \u003Cbr> PSM | MEMTO | [MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002Fb4c898eb1fb556b8d871fbe9ead92256-Abstract-Conference.html) | No | NIPS\u003Cbr>2023\n| Anomaly Detection | PSM \u003Cbr> SMD \u003Cbr> SWaT | D3R | [Drift doesn’t Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F22f5d8e689d2a011cd8ead552ed59052-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002FForestsKing\u002FD3R) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FForestsKing\u002FD3R?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FForestsKing\u002FD3R?color=critical&style=social) | NIPS\u003Cbr>2023\n| Anomaly Detection |SWaT \u003Cbr> WADI \u003Cbr> PSM \u003Cbr> MSL \u003Cbr> SMD \u003Cbr> trimSyn | Framework | [Nominality Score Conditioned Time Series Anomaly Detection by Point\u002FSequential Reconstruction](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2023\u002Fhash\u002F22f5d8e689d2a011cd8ead552ed59052-Abstract-Conference.html) | [Code](https:\u002F\u002Fgithub.com\u002Fandrewlai61616\u002FNPSR) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fandrewlai61616\u002FNPSR?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fandrewlai61616\u002FNPSR?color=critical&style=social) | NIPS\u003Cbr>2023\n| Anomaly Detection | SMD \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> PSM \u003Cbr> DND| PUAD | [Prototype-oriented unsupervised anomaly detection for multivariate time series](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fli23d.html) | [Code](https:\u002F\u002Fgithub.com\u002FLiYuxin321\u002FPUAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLiYuxin321\u002FPUAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLiYuxin321\u002FPUAD?color=critical&style=social) | ICML\u003Cbr>2023\n| Anomaly Detection |UCR \u003Cbr>SMD | surrogate | [Unsupervised Model Selection for Time Series Anomaly Detection](https:\u002F\u002Fopenreview.net\u002Fforum?id=gOZ_pKANaPW) | [Author](https:\u002F\u002Fgithub.com\u002Fmononitogoswami) | ICLR\u003Cbr>2023\n| Anomaly Detection | MSL \u003Cbr> SMAP \u003Cbr> PSM \u003Cbr> SMD | DCdetector | [DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599295) | [Code](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FKDD2023-DCdetector) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDAMO-DI-ML\u002FKDD2023-DCdetector?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDAMO-DI-ML\u002FKDD2023-DCdetector?color=critical&style=social) | KDD\u003Cbr>2023\n| Anomaly Detection | MSL \u003Cbr> SWaT \u003Cbr> WADI | PoA | [Precursor-of-Anomaly Detection for Irregular Time Series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3580305.3599469) | [Code](https:\u002F\u002Fgithub.com\u002Fsheoyon-jhin\u002FPAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsheoyon-jhin\u002FPAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsheoyon-jhin\u002FPAD?color=critical&style=social) | KDD\u003Cbr>2023\n| Anomaly Detection | MSL \u003Cbr> SWaT \u003Cbr> PSM \u003Cbr> SMAP \u003Cbr> SMD | DiffAD | [Imputation-based Time-Series Anomaly Detection with Conditional Weight-Incremental Diffusion Models](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599391) | [Code](https:\u002F\u002Fgithub.com\u002FChunjingXiao\u002FDiffAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChunjingXiao\u002FDiffAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FChunjingXiao\u002FDiffAD?color=critical&style=social) | KDD\u003Cbr>2023\n| Anomaly Detection |SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT | DAEMON | [Adversarial Autoencoder for Unsupervised Time Series Anomaly Detection and Interpretation](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570371) | [Code](https:\u002F\u002Fgithub.com\u002FSherlock-C\u002FDAEMON) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSherlock-C\u002FDAEMON?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSherlock-C\u002FDAEMON?color=critical&style=social) | AAAI\u003Cbr>2023\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> PSM \u003Cbr> MSL \u003Cbr> SMD | MTGFlow | [Detecting Multivariate Time Series Anomalies with Zero Known Label](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25623) | [Code](https:\u002F\u002Fgithub.com\u002Fzqhang\u002FMTGFLOW) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzqhang\u002FMTGFLOW?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzqhang\u002FMTGFLOW?color=critical&style=social) | AAAI\u003Cbr>2023\n| Anomaly Detection | SWaT \u003Cbr> WADI SMAP \u003Cbr> MSL | DuoGAT | [DuoGAT: Dual Time-oriented Graph Attention Networks for Accurate, Efficient and Explainable Anomaly Detection on Time-series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614857) | [Code](https:\u002F\u002Fgithub.com\u002FByeongtaePark\u002FDuoGAT) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FByeongtaePark\u002FDuoGAT?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FByeongtaePark\u002FDuoGAT?color=critical&style=social) | CIKM\u003Cbr>2023\n| Anomaly Detection | SWaT \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> PSM \u003Cbr> SMD | MadSGM | [MadSGM: Multivariate Anomaly Detection with Score-based Generative Models](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614857) | None | CIKM\u003Cbr>2023\n| Anomaly Detection |SMD \u003Cbr> Boiler | ContexTDA | [Context-aware Domain Adaptation for Time Series Anomaly Detection](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch76) | None| SDM 2023\n| Anomaly Detection | AIOps \u003Cbr> UCR | COCA | [Deep Contrastive One-Class Time Series Anomaly Detection](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611977653.ch78) | [Merlion,Tsaug ](https:\u002F\u002Fgithub.com\u002Fruiking04\u002FCOCA) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fruiking04\u002FCOCA?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fruiking04\u002FCOCA?color=critical&style=social) | SDM 2023\n| Anomaly Detection | DND \u003Cbr> SMD \u003Cbr> MSL \u003Cbr> SMAP | DVGCRN | [Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fchen22x.html) | [Future](https:\u002F\u002Fgithub.com\u002FBoChenGroup) | ICML\u003Cbr>2022\n| Anomaly Detection | YelpChi \u003Cbr> Amazon \u003Cbr> T-Finance \u003Cbr> T-Social | BWGNN | [Rethinking Graph Neural Networks for Anomaly Detection](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Ftang22b.html) | [Code](https:\u002F\u002Fgithub.com\u002FsquareRoot3\u002FRethinking-Anomaly-Detection) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FsquareRoot3\u002FRethinking-Anomaly-Detection?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FsquareRoot3\u002FRethinking-Anomaly-Detection?color=critical&style=social) | ICML\u003Cbr>2022\n| Anomaly Detection | SMD \u003Cbr> PSM \u003Cbr> MSL&SMAP \u003Cbr> SWaT \u003Cbr> NeurIPS-TS | Anomaly Transformer | [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https:\u002F\u002Fopenreview.net\u002Fforum?id=LzQQ89U1qm_) | [Code](https:\u002F\u002Fgithub.com\u002Fspencerbraun\u002Fanomaly_transformer_Code) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspencerbraun\u002Fanomaly_transformer_Code?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fspencerbraun\u002Fanomaly_transformer_Code?color=critical&style=social) | ICLR\u003Cbr>2022\n| Density Estimation & Anomaly Detection | PMU-B \u003Cbr> PMU-C \u003Cbr> SWaT \u003Cbr> METR-LA | GANF | [Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series](https:\u002F\u002Fopenreview.net\u002Fforum?id=45L_dgP48Vd) | [Code](https:\u002F\u002Fgithub.com\u002FEnyanDai\u002FGANF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEnyanDai\u002FGANF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEnyanDai\u002FGANF?color=critical&style=social) | ICLR\u003Cbr>2022\n| Anomaly Detection | | | [Anomaly Detection for Tabular Data with Internal Contrastive Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=_hszZbt46bT) | None | ICLR\u003Cbr>2022\n| Anomaly Detection | Machine-Temp \u003Cbr> NYCTaxi \u003Cbr> Twitter \u003Cbr> SWaT | algorithmic | [Local Evaluation of Time Series Anomaly Detection Algorithms](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539339) | [Python](https:\u002F\u002Fgithub.com\u002Fahstat\u002Faffiliation-metrics-py) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fahstat\u002Faffiliation-metrics-py?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fahstat\u002Faffiliation-metrics-py?color=critical&style=social) | KDD\u003Cbr>2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> HAI | FuSAGNet | [Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539117) | [Code](https:\u002F\u002Fgithub.com\u002Fsihohan\u002FFuSAGNet) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsihohan\u002FFuSAGNet?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsihohan\u002FFuSAGNet?color=critical&style=social) | KDD\u003Cbr>2022\n| Anomaly Detection | Slef-defined | RCAD | [RCAD: Real-time Collaborative Anomaly Detection System for Mobile Broadband Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539097) | [Code](https:\u002F\u002Fgithub.com\u002Fazza8903\u002FHTM-MODEL_EXCHANGE\u002F) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fazza8903\u002FHTM-MODEL_EXCHANGE\u002F?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fazza8903\u002FHTM-MODEL_EXCHANGE\u002F?color=critical&style=social) | KDD\u003Cbr>2022\n| Anomaly Detection | | AnomalyKiTS | [AnomalyKiTS-Anomaly Detection Toolkit for Time Series](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_dm318) | None | AAAI\u003Cbr>2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> MSL \u003Cbr> SMAP \u003Cbr> SMD | PA | [Towards a Rigorous Evaluation of Time-Series Anomaly Detection](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai2239) | None | AAAI\u003Cbr>2022\n| Anomaly Detection | YAHOO \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> PSM | NCAD | [Neural Contextual Anomaly Detection for Time Series](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F332) | [Future](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fgluon-ts\u002Ftree\u002Fdev\u002Fsrc\u002Fgluonts\u002Fnursery) | IJCAI\u003Cbr>2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> PSM | GRELEN | [GRELEN: Multivariate Time Series Anomaly Detection from the Perspective of Graph Relational Learning](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F394) | None| IJCAI\u003Cbr>2022\n| Anomaly Detection | MSL \u003Cbr> SMAP \u003Cbr> MNIST \u003Cbr> ,etc | CADET | [CADET: Calibrated Anomaly Detection for Mitigating Hardness Bias](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F278) | [Future](https:\u002F\u002Fgithub.com\u002Fd-ailin\u002FCADET)| IJCAI\u003Cbr>2022\n| Anomaly Detection | ECG \u003Cbr> HAR \u003Cbr> MNIST | | [Understanding and Mitigating Data Contamination in Deep Anomaly Detection: A Kernel-based Approach](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F322) | None | IJCAI\u003Cbr>2022\n| Anomaly Detection | Business| SLA-VAE | [A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3511984) | None| WWW 2022\n| Anomaly Detection | KDDCUP99 \u003Cbr> NSL \u003Cbr> UNSW, etc | MemStream | [MemStream: Memory-Based Streaming Anomaly Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3511984) | [Code](https:\u002F\u002Fgithub.com\u002FStream-AD\u002FMemStream)| \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FStream-AD\u002FMemStream?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FStream-AD\u002FMemStream?color=critical&style=social) WWW 2022\n| Anomaly Detection | GD \u003Cbr> HSS \u003Cbr> ECG \u003Cbr> NAB \u003Cbr> Yahoo S5 \u003Cbr> 2D \u003Cbr> SYN | RDAE | [Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835554) | [Author](https:\u002F\u002Fgithub.com\u002Ftungk) | ICDE 2022\n| Anomaly Detection | GD \u003Cbr> HSS \u003Cbr> ECG \u003Cbr> TD \u003Cbr> Yahoo S5 | BiVQRAEs | [Anomaly Detection in Time Series with Robust Variational Quasi-Recurrent Autoencoders](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835268) | [Code](https:\u002F\u002Fgithub.com\u002Ftungk\u002FBi-VQRAE) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftungk\u002FBi-VQRAE?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftungk\u002FBi-VQRAE?color=critical&style=social) | ICDE 2022\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> BATADAL | MAD-SGCN | [MAD-SGCN: Multivariate Anomaly Detection with Self-learning Graph Convolutional Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9835470) | None | ICDE 2022\n| Anomaly Detection | NAB \u003Cbr> UCR \u003Cbr> MBA \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> MSDS | TranAD | [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https:\u002F\u002Fdoi.org\u002F10.14778\u002F3514061.3514067) | [Code](https:\u002F\u002Fgithub.com\u002Fimperial-qore\u002FTranAD) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fimperial-qore\u002FTranAD?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fimperial-qore\u002FTranAD?color=critical&style=social) | VLDB 2022\n| Anomaly Detection | KPI \u003Cbr> Yahoo \u003Cbr> SMAP \u003Cbr> MSL | TFAD | [TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557470) | [Code](https:\u002F\u002Fgithub.com\u002Fdamo-di-ml\u002Fcikm22-tfad) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdamo-di-ml\u002Fcikm22-tfad?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdamo-di-ml\u002Fcikm22-tfad?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | SMAP \u003Cbr> MSL \u003Cbr> SMD \u003Cbr> KARI \u003Cbr> Synthetic | Attack | [Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557073) | [Code](https:\u002F\u002Fgithub.com\u002Fshahroztariq\u002FAdversarial-Attacks-on-Timeseries) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshahroztariq\u002FAdversarial-Attacks-on-Timeseries?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fshahroztariq\u002FAdversarial-Attacks-on-Timeseries?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | Cora \u003Cbr> Citeseer \u003Cbr> PubMed \u003Cbr> Flickr \u003Cbr> ogbn-arxiv | LHML | [Learning Hypersphere for Few-shot Anomaly Detection on Attributed Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557377) | [Code](https:\u002F\u002Fgithub.com\u002FEureka-GQY\u002FLHML) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEureka-GQY\u002FLHML?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEureka-GQY\u002FLHML?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | RT \u003Cbr> NetSpd | RobustDTW | [Robust Time Series Dissimilarity Measure for Outlier Detection and Periodicity Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557686) | None | CIKM\u003Cbr>2022\n| Anomaly Detection | CIFAR-1 \u003Cbr> CIFAR-10 \u003Cbr> Caltech 10 | SLA2 | [Self-supervision Meets Adversarial Perturbation: A Novel Framework for Anomaly Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557697) | [Code](https:\u002F\u002Fgithub.com\u002Fwyzjack\u002FSLA2P) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwyzjack\u002FSLA2P?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwyzjack\u002FSLA2P?color=critical&style=social) | CIKM\u003Cbr>2022\n| Anomaly Detection | SMD | FDRC | [Online false discovery rate control for anomaly detection in time series](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467075) | Nçone | NeurIPS 2021\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> ASD | InterFusion | [Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding](https:\u002F\u002Fpapers.NeurIPS.cc\u002Fpaper\u002F2021\u002Fhash\u002Fdef130d0b67eb38b7a8f4e7121ed432c-Abstract.html) | [TF](https:\u002F\u002Fgithub.com\u002Fzhhlee\u002FInterFusion) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhhlee\u002FInterFusion?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhhlee\u002FInterFusion?color=critical&style=social) | KDD\u003Cbr>2021\n| Anomaly Detection | SMD \u003Cbr> SWaT \u003Cbr> PSM \u003Cbr> BKPI | RANSynCoders | [Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467174) | [TF](https:\u002F\u002Fgithub.com\u002FeBay\u002FRANSynCoders) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FeBay\u002FRANSynCoders?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FeBay\u002FRANSynCoders?color=critical&style=social) | KDD\u003Cbr>2021\n| Anomaly Detection | PUMP \u003Cbr> WADI \u003Cbr> SWaT | NSIBF | [Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467137) | [TF](https:\u002F\u002Fgithub.com\u002FNSIBF\u002FNSIBF) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNSIBF\u002FNSIBF?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNSIBF\u002FNSIBF?color=critical&style=social) | KDD\u003Cbr>2021\n| Anomaly Detection | SWaT \u003Cbr> WADI | GDN | [Graph Neural Network-Based Anomaly Detection in Multivariate Time Series](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16523) | [Code](https:\u002F\u002Fgithub.com\u002Fd-ailin\u002FGDN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fd-ailin\u002FGDN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fd-ailin\u002FGDN?color=critical&style=social) | AAAI\u003Cbr>2021\n| Anomaly Detection | SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> SWaT | DAEMON | [DAEMON: Unsupervised Anomaly Detection and Interpretation for Multivariate Time Series](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458835) | [Future](https:\u002F\u002Fgithub.com\u002FAzerrroth\u002FDAEMON) | ICDE 2021\n| Anomaly Detection | KPI \u003Cbr> Yahoo | FluxEV | [FluxEV: A Fast and Effective Unsupervised Framework for Time-Series Anomaly Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441823) | [Py](https:\u002F\u002Fgithub.com\u002Fjlidw\u002FFluxEV) | WSDM 2021\n| Anomaly Detection | [DataLink](https:\u002F\u002Fcompete.hexagon-ml.com\u002Fpractice\u002Fcompetition\u002F39\u002F)| Benchmark | [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9537291) | None | TKDE 2021\n| Earthquakes Detection | NIED | CrowdQuake | [A Networked System of Low-Cost Sensors for Earthquake Detection via Deep Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403378) | [TF](https:\u002F\u002Fgithub.com\u002Fxhuang2016\u002FSeismic-Detection) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxhuang2016\u002FSeismic-Detection?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fxhuang2016\u002FSeismic-Detection?color=critical&style=social) | KDD\u003Cbr>2020\n| Anomaly Detection | SWaT \u003Cbr> WADI \u003Cbr> SMD \u003Cbr> SMAP \u003Cbr> MSL \u003Cbr> Orange | USAD | [USAD: UnSupervised Anomaly Detection on Multivariate Time Series](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403392) | [Code](https:\u002F\u002Fgithub.com\u002Fmanigalati\u002Fusad) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmanigalati\u002Fusad?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmanigalati\u002Fusad?color=critical&style=social) | KDD\u003Cbr>2020\n| Anomaly Detection | NYC | CHAT | [Cross-interaction hierarchical attention networks for urban anomaly prediction](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.5555\u002F3491440.3492041) | None | IJCAI\u003Cbr>2020\n| Anomaly Detection | NYC-Bike \u003Cbr> NYC-Taxi \u003Cbr> Weather \u003Cbr> NYC-POI \u003Cbr> NYC-Anomaly | DST-MFN | [Deep Spatio-Temporal Multiple Domain Fusion Network for Urban Anomalies Detection](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411920) | None | CIKM\u003Cbr>2020\n| Anomaly Detection | SMAP \u003Cbr> MSL \u003Cbr> TSA | MTAD-GAT | [Multivariate Time-Series Anomaly Detection via Graph Attention Network](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338317) | [TF](https:\u002F\u002Fgithub.com\u002Fmangushev\u002Fmtad-gat) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmangushev\u002Fmtad-gat?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmangushev\u002Fmtad-gat?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002FML4ITS\u002Fmtad-gat-Code) | ICDM 2020\n| Anomaly Detection | SMAP \u003Cbr> MSL \u003Cbr> SMD | OmniAnomaly | [Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330672) | [TF](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002FOmniAnomaly) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNetManAIOps\u002FOmniAnomaly?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNetManAIOps\u002FOmniAnomaly?color=critical&style=social) | KDD\u003Cbr>2019\n| Anomaly Detection | GeoLife \u003Cbr> TST | IRL-ADU | [Sequential Anomaly Detection using Inverse Reinforcement Learning](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330932) | None | KDD\u003Cbr>2019\n| Anomaly Detection | donors \u003Cbr> census \u003Cbr> fraud \u003Cbr> celeba ,etc | DevNet | [Deep Anomaly Detection with Deviation Networks](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330871) | [Keras](https:\u002F\u002Fgithub.com\u002FGuansongPang\u002Fdeviation-network) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGuansongPang\u002Fdeviation-network?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGuansongPang\u002Fdeviation-network?color=critical&style=social) [Code](https:\u002F\u002Fgithub.com\u002FChoubo\u002Fdeviation-network-image) | KDD\u003Cbr>2019\n| Anomaly Detection | KPI \u003Cbr> Yahoo \u003Cbr> Microsoft | SR-CNN | [Time-Series Anomaly Detection Service at Microsoft](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330680) | None | KDD\u003Cbr>2019\n| Anomaly Detection | power plant | MSCRED | [A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3942) | [TF](https:\u002F\u002Fgithub.com\u002F7fantasysz\u002FMSCRED) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002F7fantasysz\u002FMSCRED?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002F7fantasysz\u002FMSCRED?color=critical&style=social) | AAAI\u003Cbr>2019\n| Anomaly Detection | ECG \u003Cbr> Motion | BeatGAN | [BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0616.pdf) | [Code](https:\u002F\u002Fgithub.com\u002Fhi-bingo\u002FBeatGAN) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhi-bingo\u002FBeatGAN?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhi-bingo\u002FBeatGAN?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Anomaly Detection | NAB \u003Cbr> ECG | OED | [Outlier Detection for Time Series with Recurrent Autoencoder Ensembles](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0378.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Ftungk\u002FOED) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftungk\u002FOED?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftungk\u002FOED?color=critical&style=social) | IJCAI\u003Cbr>2019\n| Anomaly Detection | KPIs | Buzz | [Unsupervised Anomaly Detection for Intricate KPIs via Adversarial Training of VAE](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8737430) | [TF](https:\u002F\u002Fgithub.com\u002Fyantijin\u002FBuzz) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyantijin\u002FBuzz?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyantijin\u002FBuzz?color=critical&style=social) | INFOCOM 2019\n| Anomaly Detection | KDDCUP \u003Cbr> Thyroid \u003Cbr> Arrhythmia \u003Cbr> KDDCUP-Rev | DAGMM | [Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection](https:\u002F\u002Fopenreview.net\u002Fforum?id=BJJLHbb0-) | [Code](https:\u002F\u002Fgithub.com\u002Fdanieltan07\u002Fdagmm) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdanieltan07\u002Fdagmm?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdanieltan07\u002Fdagmm?color=critical&style=social) | ICLR\u003Cbr>2018\n| Anomaly Detection | SMAP \u003Cbr> MSL | telemanom | [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3219819.3219845) | [TF](https:\u002F\u002Fgithub.com\u002Fkhundman\u002Ftelemanom) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkhundman\u002Ftelemanom?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkhundman\u002Ftelemanom?color=critical&style=social) | KDD\u003Cbr>2018\n| Anomaly Detection | AD \u003Cbr> AID362 \u003Cbr> aPascal \u003Cbr> BM , etc| CINFO | [Sparse Modeling-Based Sequential Ensemble Learning for Effective Outlier Detection in High-Dimensional Numeric Data](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11692) | [Matlab](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F0B_GL5U7rPj1xNzNwTHpHSzZkQXM\u002Fview?resourcekey=0-HneFEhC8NUIWDfhmfaOyBQ) | AAAI\u003Cbr>2018\n| Anomaly Detection | KPIs | Donut | [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3178876.3185996) | [TF](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002Fdonut) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNetManAIOps\u002Fdonut?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNetManAIOps\u002Fdonut?color=critical&style=social) | WWW 2018\n| Anomaly Detection | MAWI | DSPOT | [Anomaly Detection in Streams with Extreme Value Theory](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3097983.3098144) | [Python](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002Fdonut) \u003Cbr>![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNetManAIOps\u002Fdonut?color=critical&style=social) \u003Cbr>![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNetManAIOps\u002Fdonut?color=critical&style=social) | KDD\u003Cbr>2017\n| Anomaly Detection | Power \u003Cbr> Space \u003Cbr> Engine \u003Cbr> ECG | EncDec-AD | [ LSTM-based encoder-decoder for multi-sensor anomaly detection](https:\u002F\u002Fwww.semanticscholar.org\u002Fpaper\u002FLSTM-based-Encoder-Decoder-for-Multi-sensor-Anomaly-Malhotra-Ramakrishnan\u002Fe9672150c4f39ab64876e798a94212a93d1770fe) | [Code](https:\u002F\u002Fgithub.com\u002Fjaeeun49\u002FAnomaly-Detection\u002Fblob\u002Fmain\u002Fcode_practices\u002FLSTM-based%20Encoder-Decoder%20for%20Multi-sensor%20Anomaly%20Detection.ipynb) | ICML\u003Cbr>2016\n| Anomaly Detection | MORE | MORE | [https:\u002F\u002Fgithub.com\u002FZIYU-DEEP\u002FIJCAI-Paper-List-of-Anomaly-Detection](https:\u002F\u002Fgithub.com\u002FZIYU-DEEP\u002FIJCAI-Paper-List-of-Anomaly-Detection) | MORE | IJCAI\n| Anomaly Detection | MORE | MORE | [DeepTimeSeriesModel](https:\u002F\u002Fgithub.com\u002Fdrzhang3\u002FDeepTimeSeriesModel) | MORE | MORE\n| Anomaly Detection | MORE | MORE | [GuansongPang](https:\u002F\u002Fgithub.com\u002FGuansongPang\u002FSOTA-Deep-Anomaly-Detection) | MORE | MORE\n\n\n\n# [需求预测](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表 |\n| :-: | :-: | :-: | :-: | :-:| - |\n| 论文数量：30+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| 出行\u003Cbr>需求 | CDP \u003Cbr> SLD | STTD | [基于时空 Tweedie 模型的不确定性量化：用于零膨胀且长尾分布的出行需求预测](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614918) | [代码](https:\u002F\u002Fgithub.com\u002FSTTDAnonymous\u002FSTTD) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSTTDAnonymous\u002FSTTD?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSTTDAnonymous\u002FSTTD?color=critical&style=social) | CIKM\u003Cbr>2023\n| 出行\u003Cbr>需求 | NYC Bike \u003Cbr> NYC Taxi | AGND | [用于交通需求预测的自适应图神经扩散模型](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3615153) | 无 | CIKM\u003Cbr>2023\n| 交通需求 | BJSubway \u003Cbr> NYCTaxi | CMOD | [面向起讫点需求预测的连续时间与多层级图表示学习](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539273) | [代码](https:\u002F\u002Fgithub.com\u002Fliangzhehan\u002FCMOD) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliangzhehan\u002FCMOD?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliangzhehan\u002FCMOD?color=critical&style=social) | KDD\u003Cbr>2022\n| 职位需求 | IT \u003Cbr> FIN \u003Cbr> CONS | DH-GEM | [基于动态异质图增强元学习的人才供需联合预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539139) | [代码](https:\u002F\u002Fgithub.com\u002Fgzn00417\u002FDH-GEM) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgzn00417\u002FDH-GEM?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgzn00417\u002FDH-GEM?color=critical&style=social) | KDD\u003Cbr>2022\n| 供给与\u003Cbr>需求 | JONAS-NYC \u003Cbr> JONAS-DC \u003Cbr> COVID-CHI \u003Cbr> COVID-US | EAST-Net | [事件感知的多模态出行即时预报](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai10914) | [代码](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FEAST-Net) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FEAST-Net?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FEAST-Net?color=critical&style=social) | AAAI\u003Cbr>2022\n| 健康需求 | Family Van | framework | [利用公共数据预测移动医疗诊所的需求](https:\u002F\u002Faaai-2022虚拟会议.poster_emer91) | 无 | AAAI\u003Cbr>2022\n| 交通需求 | BJMetro \u003Cbr> NYCTaxi | HMOD | [基于层次化记忆的动态图学习：用于起讫点需求预测](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F331) | [代码](https:\u002F\u002Fgithub.com\u002FRising0321\u002FHMOD) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRising0321\u002FHMOD?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRising0321\u002FHMOD?color=critical&style=social) | IJCAI\u003Cbr>2022\n| 交通需求 | Chicago \u003Cbr> LosAngeles | STGNN-DJD | [一种数据驱动的时空图神经网络，用于锁车式自行车需求预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9835338) | [代码](https:\u002F\u002Fgithub.com\u002FGuanyaoLI\u002FSTGNN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGuanyaoLI\u002FSTGNN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGuanyaoLI\u002FSTGNN?color=critical&style=social) | ICDE 2022\n| OD需求 | Shanghai \u003Cbr> Changsha \u003Cbr> Beijing | CausalOD | [因果学习赋能的城市规划起讫点需求预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557255) | [代码](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FSIRI) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FSIRI?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FSIRI?color=critical&style=social) | CIKM\u003Cbr>2022\n| OD需求 | NYC Taxi \u003Cbr> Haikou \u003Cbr> SZMetro | HSTN | [基于混合时空网络的起讫点交通预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027683) | [TF](https:\u002F\u002Fgithub.com\u002Fchentingyang\u002FHSTN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchentingyang\u002FHSTN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchentingyang\u002FHSTN?color=critical&style=social) | ICDM 2022\n| 交通需求 | NYC Bike \u003Cbr> NYC Taxi | CCRNN | [用于交通需求预测的耦合层间图卷积](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16591) | [代码](https:\u002F\u002Fgithub.com\u002FEssaim\u002FCGCDemandPrediction) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEssaim\u002FCGCDemandPrediction?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEssaim\u002FCGCDemandPrediction?color=critical&style=social) | AAAI\u003Cbr>2021\n| 交通需求 | BaiduBJ \u003Cbr> BaiduSH | Ada-MSTNet | [社区感知的多任务交通需求预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16107) | 无 | AAAI\u003Cbr>2021\n| 职位需求 | 在线 | TDAN | [基于注意力神经序列模型的人才需求预测](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467131) | 无 | KDD\u003Cbr>2021\n| 救护车需求 | Tokyo | EMS-Pred | [通过异构多图神经网络，结合人群流动特征预测救护车需求](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458623) | [代码](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FEMS-Pred-ICDE-21) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FEMS-Pred-ICDE-21?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FEMS-Pred-ICDE-21?color=critical&style=social) | ICDE 2021\n| 乘客需求 | TaxiNYC | SOUP | [SOUP：一个用于乘客需求预测和竞争性出租车供给管理的车队管理系统](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458616) | 无 | ICDE 2021\n| 乘客需求 | DiDiBJ \u003Cbr> DiDiSH| Gallat | [Gallat：一个用于乘客需求预测的时空图注意力网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458919) | 无 | ICDE 2021\n| 交通需求\u003Cbr>交通流量 | Chengdu \u003Cbr> Xian| DeepTP | [一种有效的旅行需求与交通流量联合预测模型](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458698) | 无 | ICDE 2021\n| 交通需求 | DiDiCD \u003Cbr> NYCTaxi | DAGNN | [动态自结构化图神经网络——一种用于起讫点需求预测的联合学习框架](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9657493) | 无 | TKDE 2021\n| 交通需求 | TaxiNYC \u003Cbr> CitiBikeNYC | MultiAttConvLSTM | [多级注意力网络用于全市范围内的多步乘客需求预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8873676\u002F) | 无 | TKDE 2021\n| 市场需求 | Juhuasuan \u003Cbr> Tiantiantemai | RMLDP | [关系感知的元学习：用于记录有限的电商市场细分需求预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441750) | 无 | WSDM 2021\n| 地铁\u003Cbr>需求 | MetroBJ2016 \u003Cbr> MetroBJ2018 | CAS | [城市轨道交通系统中的短期起讫点需求预测：一种通道注意力分割卷积神经网络方法](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.trc.2020.102928) | 无 | 《Transportation Research Part C》2021\n| 地铁\u003Cbr>需求 | MetroBJ2016 \u003Cbr> MetroBJ2018 | ST-ED | [利用时空编码器-解码器残差多图卷积网络预测起讫点乘车需求](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.trc.2020.102858) | 无 | 《Transportation Research Part C》2021\n| 交通需求 | Seattlebike | FairST | [公平意识导向的新出行方式需求预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5458) | 无 | AAAI\u003Cbr>2020\n| 药物需求 | Wikipedia | 无 | [利用维基百科浏览量预测药物需求：来自暗网市场的证据](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380022) | 无 | WWW 2020\n| 交通需求 | DiDiBJ \u003Cbr> DiDiSH | MPGCN | [通过多视角图卷积网络预测起讫点流量](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9101359) | [代码](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FMPGCN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FMPGCN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FMPGCN?color=critical&style=social) | ICDE 2020\n| 交通需求 | NYC \u003Cbr> DiDiCD | MPGCN | [使用双阶段图卷积、循环神经网络进行随机起讫点矩阵预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9101647\u002F) | [TF](https:\u002F\u002Fgithub.com\u002Fhujilin1229\u002Fod-pred) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhujilin1229\u002Fod-pred?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhujilin1229\u002Fod-pred?color=critical&style=social) | ICDE 2020\n| 交通需求 | Bengaluru \u003Cbr> NYC | GraphLSTM | [网格 vs 图：划分空间以改进出租车供需预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9099450\u002F) | [代码](https:\u002F\u002Fgithub.com\u002FNDavisK\u002FGrids-versus-Graphs) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNDavisK\u002FGrids-versus-Graphs?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNDavisK\u002FGrids-versus-Graphs?color=critical&style=social) | TITS 2020\n| 交通需求 | NYCbike \u003Cbr> NYCtaxi | CoST-Net | [基于深度时空神经网络的多种交通需求联合预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330887) | 无 | KDD\u003Cbr>2019\n| 交通需求 | UCAR \u003Cbr> DiDiCD | GEML | [通过图卷积预测起讫点矩阵：乘客需求建模的新视角](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330877) | [Keras](https:\u002F\u002Fgithub.com\u002FZekun-Cai\u002FGEML-Origin-Destination-Matrix-Prediction-via-Graph-Convolution) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZekun-Cai\u002FGEML-Origin-Destination-Matrix-Prediction-via-Graph-Convolution?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FZekun-Cai\u002FGEML-Origin-Destination-Matrix-Prediction-via-Graph-Convolution?color=critical&style=social) | KDD\u003Cbr>2019\n| 交通需求 | NYCbike \u003Cbr> Meso West | CE-LSTM | [学习异质时空表示以预测共享单车需求](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3890) | 无 | AAAI\u003Cbr>2019\n| 交通需求 | Beijing \u003Cbr> Shanghai | STMGCN | [时空多图卷积网络用于网约车需求预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4247) | [代码](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FST-MGCN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) | AAAI\u003Cbr>2019\n| 交通需求 | NYC-TOD | CSTN | [情境化的时空网络用于出租车起讫点需求预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8720246\u002F) | [Keras](https:\u002F\u002Fgithub.com\u002Fliulingbo918\u002FCSTN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliulingbo918\u002FCSTN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliulingbo918\u002FCSTN?color=critical&style=social) | TITS 2019\n| 交通需求 | NYCtaxi | MultiConvLSTM | [深层多尺度卷积 LSTM 网络用于旅行需求及起讫点预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8758916\u002F) | 无 | TITS 2019\n| 交通需求 | PEMS | t-SNE | [利用高粒度多源交通数据估算多年期起讫点需求](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.trc.2018.09.002) | 无 | 《Transportation Research Part C》2018\n\n\u003C!-- | 交通需求 | 电力 \u003Cbr> 交通 \u003Cbr> 纽约出租车 \u003Cbr> Uber | 框架 | [基于时间注意力学习的多时间尺度时间序列预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330662) | [代码](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FST-MGCN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FST-MGCN?color=critical&style=social) | KDD\u003Cbr>2019 \n-->\n\n\n\n# [时间序列生成](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表 |\n| :-: | :-: | :-: | :-: | :-: | - |\n| 论文数量：6 | \u003Cimg width=90\u002F> | | | | \u003Cimg width=320\u002F> |\n| TS生成 | 股票 \u003Cbr> 能源 \u003Cbr> MuJoCo | ImagenTime | [利用图像变换和扩散模型进行短时与长时时间序列的生成建模](https:\u002F\u002Fopenreview.net\u002Fforum?id=2NfBBpbN9x) | [代码](https:\u002F\u002Fgithub.com\u002Fazencot-group\u002FImagenTime) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fazencot-group\u002FImagenTime?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fazencot-group\u002FImagenTime?color=critical&style=social) | NIPS\u003Cbr>2024\n| TS生成 | AR1 \u003Cbr> 股票 \u003Cbr> 能源 \u003Cbr> 温度 \u003Cbr> 心电图 | FIDE | [FIDE：面向极端情况感知的时间序列条件扩散模型](https:\u002F\u002Fopenreview.net\u002Fforum?id=5HQhYiGnYb) | [代码](https:\u002F\u002Fgithub.com\u002Fgalib19\u002FFIDE) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgalib19\u002FFIDE?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgalib19\u002FFIDE?color=critical&style=social) | NIPS\u003Cbr>2024\n| TS生成 | 电力 \u003Cbr> 交通 \u003Cbr> 交易所 \u003Cbr> M4 \u003Cbr> UberTLC \u003Cbr> 太阳能 \u003Cbr> KDDCup \u003Cbr> 维基百科 | ANT | [ANT：时间序列扩散模型的自适应噪声调度](https:\u002F\u002Fopenreview.net\u002Fforum?id=1ojAkTylz4) | [glounts](https:\u002F\u002Fgithub.com\u002Fseunghan96\u002FANT) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseunghan96\u002FANT?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fseunghan96\u002FANT?color=critical&style=social) | NIPS\u003Cbr>2024\n| TS生成 | 正弦波 \u003Cbr> 股票 \u003Cbr> ETTh \u003Cbr> MuJoCo \u003Cbr> 能源 \u003Cbr> 太阳能 \u003Cbr> fMRI | SDformer | [SDformer：基于相似性驱动的离散Transformer用于时间序列生成](https:\u002F\u002Fopenreview.net\u002Fforum?id=ZKbplMrDzI) | [代码](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002FSDformer-main\u002FREADME.md) | NIPS\u003Cbr>2024\n| TS生成 | 正弦波 \u003Cbr> 股票 \u003Cbr> ETTh \u003Cbr> MuJoCo \u003Cbr> 能源 \u003Cbr> 太阳能 \u003Cbr> fMRI | Diffusion-TS | [Diffusion-TS：可解释的扩散模型用于通用时间序列生成](https:\u002F\u002Fopenreview.net\u002Fforum?id=4h1apFjO99) | [代码](https:\u002F\u002Fgithub.com\u002FY-debug-sys\u002FDiffusion-TS) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FY-debug-sys\u002FDiffusion-TS?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FY-debug-sys\u002FDiffusion-TS?color=critical&style=social) | ICLR\u003Cbr>2024\n| TS生成 | FRED-MD \u003Cbr> NN5 Daily \u003Cbr> 温度 雨量 \u003Cbr> 太阳能 周报 | LS4 | [用于时间序列生成的深度潜在状态空间模型](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fzhou23i.html) | [代码](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) | ICML\u003Cbr>2023\n| TS生成 | He ́non映射 \u003Cbr> 洛伦兹系统 \u003Cbr> fMRI \u003Cbr> EEG| CR-VAE | [用于医学时间序列生成的因果循环变分自编码器](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26031) | [代码](https:\u002F\u002Fgithub.com\u002Fhongmingli1995\u002FCR-VAE) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) | AAAI\u003Cbr>2023\n| TS生成 | ETTh1 \u003Cbr> ETTh2 \u003Cbr> 美国出生率 \u003Cbr> ILI| AEC-GAN | [AEC-GAN：对抗式误差校正GAN用于自回归长时时间序列生成](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26208) | [代码](https:\u002F\u002Fgithub.com\u002Fhongmingli1995\u002FCR-VAE) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhongmingli1995\u002FCR-VAE?color=critical&style=social) | AAAI\u003Cbr>2023\n| TS生成 | UCR | TimeVQVAE | [基于双向先验模型的向量化量化时间序列生成](https:\u002F\u002Fproceedings.mlr.press\u002Fv206\u002Flee23d.html) | [代码](https:\u002F\u002Fgithub.com\u002FML4ITS\u002FTimeVQVAE) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FML4ITS\u002FTimeVQVAE?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FML4ITS\u002FTimeVQVAE?color=critical&style=social) | AISTATS 2023 \n| TS生成 | USHCN \u003Cbr> KDD-CUP \u003Cbr> MIMIC-III| DGM | [基于动态高斯混合的深度生成模型，用于稀疏多变量时间序列的稳健预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16145) | [代码](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthuwuyinjun\u002FDGM2?color=critical&style=social) | AAAI\u003Cbr>2021\n\n# [出行时间估计](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表期刊 |\n| :-: | :-: | :-: | :-: | :-: | - |\n| 论文数量：20+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| 包裹配送\u003Cbr>TTE | 菜鸟 | GMDNet | [GMDNet: 基于图的混合密度网络用于估计包裹多模态出行时间分布](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25578) | [代码](https:\u002F\u002Fgithub.com\u002Fmaoxiaowei97\u002FGMDNet) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmaoxiaowei97\u002FGMDNet?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmaoxiaowei97\u002FGMDNet?color=critical&style=social) | AAAI\u003Cbr>2023\n| 配送\u003Cbr>时间估计 | 威海\u003Cbr>杭州 | IGT | [用于配送时间估计的归纳图变换器](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570409) | [代码](https:\u002F\u002Fgithub.com\u002Fenoche\u002FIGT-WSDM23) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fenoche\u002FIGT-WSDM23?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fenoche\u002FIGT-WSDM23?color=critical&style=social) | WSDM 2023\n| 配送\u003Cbr>时间估计 | 京东和亚马逊 | STTD | [基于时空 Tweedie 模型的不确定性量化，用于零膨胀且长尾的出行需求预测](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3615215) | [代码](https:\u002F\u002Fgithub.com\u002FJD-HST-GT\u002FHST-GT) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJD-HST-GT\u002FHST-GT?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJD-HST-GT\u002FHST-GT?color=critical&style=social) | CIKM\u003Cbr>2023\n| TTE | 济南市\u003Cbr>南京市 | GBTTE | [GBTTE: 基于图注意力网络的公交出行时间估计](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614730) | 无 | CIKM\u003Cbr>2023\n| TTE | 北京\u003Cbr>广州 | HierETA | [从多视角解读轨迹：用于估计到达时间的层次自注意力网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539051) | [代码](https:\u002F\u002Fgithub.com\u002FYuejiaoGong\u002FHierETA) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYuejiaoGong\u002FHierETA?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYuejiaoGong\u002FHierETA?color=critical&style=social) | KDD\u003Cbr>2022\n| TTE | 北京\u003Cbr>波尔图 | MetaER-TTE | [MetaER-TTE: 一种用于途中出行时间估计的自适应元学习模型](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F281) | 无 | IJCAI\u003Cbr>2022\n| TTE | 北京\u003Cbr>上海\u003Cbr>天津 | DuETA | [DuETA: 通过高效的图学习建模交通拥堵传播模式，用于百度地图的 ETA 预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557091) | 无 | CIKM\u003Cbr>2022\n| TTE | 百度：\u003Cbr>太原\u003Cbr>惠州\u003Cbr>合肥| SSML | [SSML: 百度地图中用于途中出行时间估计的自监督元学习器](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467060) | [Paddle](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FResearch\u002Ftree\u002Fmaster\u002FST_DM\u002FKDD2021-SSML) | KDD\u003Cbr>2021\n| TTE | 滴滴：\u003Cbr>沈阳 | HetETA | [HetETA: 用于估计到达时间的异质信息网络嵌入](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403294) | [TF](https:\u002F\u002Fgithub.com\u002Fdidi\u002Fheteta) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdidi\u002Fheteta?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdidi\u002Fheteta?color=critical&style=social) | KDD\u003Cbr>2020\n| TTE | 滴滴：\u003Cbr>北京\u003Cbr>苏州\u003Cbr>沈阳 | CompactETA | [CompactETA: 一个用于出行时间预测的快速推理系统](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403386) | 无 | KDD\u003Cbr>2020\n| TTE | GTFS | BusTr | [BusTr: 根据实时交通情况预测公交车出行时间](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403376) | 无 | KDD\u003Cbr>2020\n| TTE | 太原\u003Cbr>合肥\u003Cbr>惠州\u003Cbr>（百度） | BusTr | [ConSTGAT: 用于百度地图出行时间估计的上下文时空图注意力网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403320) | 无 | KDD\u003Cbr>2020\n| TTE | 纽约\u003Cbr>伊斯坦布尔\u003Cbr>东京 | DeepJMT | [用于联合出行与时间预测的上下文感知深度模型](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3336191.3371837) | 无 | WSDM 2020\n| TTE | 北京\u003Cbr>上海 | TTPNet | [TTPNet: 基于张量分解和图嵌入的出行时间预测神经网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9261122) | [代码](https:\u002F\u002Fgithub.com\u002FYibinShen\u002FTTPNet) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYibinShen\u002FTTPNet?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYibinShen\u002FTTPNet?color=critical&style=social) | TKDE 2020\n| TTE | DiDiBJ | RNML-ETA | [用于估计到达时间的道路网络度量学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9412145) | 无 | ICPR 2020\n| TTE | 菜鸟 | DeepETA | [DeepETA: 一种用于包裹配送系统中估计到达时间的时空序列神经网络模型](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3856) | 无 | AAAI\u003Cbr>2019\n| TTE | 北京\u003Cbr>上海 | CTTE | [激进驾驶真的能节省更多时间吗？用于定制化出行时间估计的多任务学习](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0234.pdf) | 无 | IJCAI\u003Cbr>2019\n| TTE | 上海\u003Cbr>波尔图 | DeepI2T | [无需路网的出行时间估计：一种基于城市形态布局表示的方法](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0245.pdf) | 无 | IJCAI\u003Cbr>2019\n| TTE | 波尔图\u003Cbr>成都 | DeepIST | [DeepIST: 基于深度图像的时空网络用于出行时间估计](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3357870) | [TF](https:\u002F\u002Fgithub.com\u002Fcsiesheep\u002Fdeepist) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcsiesheep\u002Fdeepist?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcsiesheep\u002Fdeepist?color=critical&style=social) | CIKM\u003Cbr>2019\n| TTE | 新加坡 | AtHy-TNet | [使用属性相关混合轨迹网络进行路径出行时间估计](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357927) | 无 | CIKM\u003Cbr>2019\n| TTE | BT-交通\u003Cbr>PEMS07\u003Cbr>Q-交通 | NASF | [学习有效估计最快路线推荐的出行时间](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357907) | 无 | CIKM\u003Cbr>2019\n| TTE | 成都\u003Cbr>北京 | DeepTTE | [你什么时候到？基于深度神经网络的出行时间估计](https:\u002F\u002Fjelly007.github.io\u002FdeepTTE.pdf) | [代码](https:\u002F\u002Fgithub.com\u002FUrbComp\u002FDeepTTE) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUrbComp\u002FDeepTTE?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUrbComp\u002FDeepTTE?color=critical&style=social) | AAAI\u003Cbr>2018\n| TTE | 波尔图\u003Cbr>旧金山 | NoisyOR | [通过建模主干道之间的异质影响来预测车辆出行时间](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11858) | 无 | AAAI\u003Cbr>2018\n| TTE | 更多 | MORE | [github](https:\u002F\u002Fgithub.com\u002FNickHan-cs\u002FSpatio-Temporal-Data-Mining-Survey\u002Fblob\u002Fmaster\u002FEstimated-Time-of-Arrival\u002FPaper.md) | 更多 | 更多\n\n\u003C!--\n\n| TTE | GTFS 北京 | BusTr | [BusTr：基于实时交通数据预测公交车运行时间](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403320) | [代码](https:\u002F\u002Fgithub.com\u002FUrbComp\u002FDeepTTE) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FUrbComp\u002FDeepTTE?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FUrbComp\u002FDeepTTE?color=critical&style=social) | AAAI\u003Cbr>2018 -->\n\n# [交通位置预测](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表 |\n| :-: | :-: | :-: | :-: |:-: | - |\n| 论文数量：20 | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=310\u002F> |\n| 地点 | ETH+UCY \u003Cbr> SDD \u003Cbr> nuScenes \u003Cbr> SportVU | | [你多半独自前行：轨迹预测中的特征归因分析](https:\u002F\u002Fopenreview.net\u002Fforum?id=POxF-LEqnF) | 无 | ICLR\u003Cbr>2022\n| 地点 | 北京 \u003Cbr> 波尔图 | MetaPTP | [MetaPTP：一种自适应元优化的个性化空间轨迹预测模型](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539360) | [Kai Zheng](http:\u002F\u002Fzheng-kai.com\u002F) 代码-无 | KDD\u003Cbr>2022\n| 地点 | BaiduApollo \u003Cbr> NGSIM | HeGA | [HeGA：用于高密度交通中轨迹预测的异构图聚合网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557345) | [代码](https:\u002F\u002Fgithub.com\u002FGCDAN\u002FGCDAN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGCDAN\u002FGCDAN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGCDAN\u002FGCDAN?color=critical&style=social) | CIKM\u003Cbr>2022\n| 地点 | ETH \u003Cbr> 酒店 \u003Cbr> 大学 \u003Cbr> Zara1 \u003Cbr> Zara2 | SGTN | [复杂社交场景下行人轨迹预测的社会图变换网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557455) | [代码](https:\u002F\u002Fgithub.com\u002FGCDAN\u002FGCDAN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGCDAN\u002FGCDAN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGCDAN\u002FGCDAN?color=critical&style=social) | CIKM\u003Cbr>2022\n| 地点 | Gowalla \u003Cbr> Foursquare \u003Cbr> WiFi-Trace | GCDAN | [通过图卷积双注意力网络预测人类移动](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3488560.3498400) | [代码](https:\u002F\u002Fgithub.com\u002FGCDAN\u002FGCDAN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FGCDAN\u002FGCDAN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FGCDAN\u002FGCDAN?color=critical&style=social) | WSDM 2022\n| 地点 | MI \u003Cbr> SIP | CMT-Net | [CMT-Net：一种考虑相互转移的出租车上下客联合预测框架](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3488560.3498394) | 无 | WSDM 2022\n| 地点 | Gowalla \u003Cbr> FS-NYC \u003Cbr> FS-TKY | MobTCast | [MobTCast：利用辅助轨迹预测进行人类移动预测](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Ffecf2c550171d3195c879d115440ae45-Abstract.html) | [作者](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1xfiaz9cAxKYmNWgOH986JpMVSQbt3_qu?usp=sharing) | NeurIPS 2021\n| 地点 | ETH \u003Cbr> 酒店 \u003Cbr> 大学 \u003Cbr> Zara1 \u003Cbr> Zara2 | CARPe | [CARPe Posterum：一种用于实时行人路径预测的卷积方法](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16335) | [代码](https:\u002F\u002Fgithub.com\u002FTeCSAR-UNCC\u002FCARPe_Posterum) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) | AAAI\u003Cbr>2021\n| 地点 | ETH \u003Cbr> 酒店 \u003Cbr> 大学 \u003Cbr> Zara1 \u003Cbr> Zara2 | TPNMS | [具有多监督的行人轨迹预测时间金字塔网络](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16299) | [代码](https:\u002F\u002Fgithub.com\u002FBlessinglrq\u002FTPNMS) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBlessinglrq\u002FTPNMS?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBlessinglrq\u002FTPNMS?color=critical&style=social) | AAAI\u003Cbr>2021\n| 地点 | ETH \u003Cbr> 酒店 \u003Cbr> 大学 \u003Cbr> Zara1 \u003Cbr> Zara2 | DMRGCN | [解耦的多关系图卷积网络用于行人轨迹预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16174) | [代码](https:\u002F\u002Fgithub.com\u002FTeCSAR-UNCC\u002FCARPe_Posterum) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FTeCSAR-UNCC\u002FCARPe_Posterum?color=critical&style=social) | AAAI\u003Cbr>2021\n| 地点 | Gowalla \u003Cbr> Foursquare | BSDA | [位置预测你：基于双向推测与双层关联的位置预测](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F74) | 无 | IJCAI\u003Cbr>2021\n| 地点 | ETH-UCY \u003Cbr> 碰撞 \u003Cbr> NGsim \u003Cbr> Charges \u003Cbr> NBA | FQA | [基于模糊查询注意力的多智能体轨迹预测](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Ffe87435d12ef7642af67d9bc82a8b3cd-Abstract.html) | [代码](https:\u002F\u002Fgithub.com\u002Fnitinkamra1992\u002FFQA) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fnitinkamra1992\u002FFQA?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fnitinkamra1992\u002FFQA?color=critical&style=social) | NeurIPS 2020\n| 地点 | ETH-UCY \u003Cbr> 碰撞 \u003Cbr> NGsim \u003Cbr> Charges \u003Cbr> NBA | ARNN | [一种用于个性化下一处位置推荐的注意力循环神经网络](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5337) | 无 | AAAI\u003Cbr>2020\n| 地点 | ETH \u003Cbr> 酒店 \u003Cbr> 大学 \u003Cbr> Zara1 \u003Cbr> Zara2 | MDNLSTM | [拥挤空间中多模态交互感知的轨迹预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6874) | 无 | AAAI\u003Cbr>2020\n| 地点 | 大西洋| OMuLeT | [OMuLeT：用于飓风路径预报的在线多提前期位置预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5444) | [Matlab](https:\u002F\u002Fgithub.com\u002Fcqwangding\u002FOMuLeT) | AAAI\u003Cbr>2020\n| 地点 | Gowalla \u003Cbr> Foursquare | Flashback | [OMuLeT：用于飓风路径预报的在线多提前期位置预测](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F302) | [代码](https:\u002F\u002Fgithub.com\u002FeXascaleInfolab\u002FFlashback_code) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FeXascaleInfolab\u002FFlashback_code?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FeXascaleInfolab\u002FFlashback_code?color=critical&style=social) | IJCAI\u003Cbr>2020\n| 地点 | CrowdCJ \u003Cbr> 垃圾箱 \u003Cbr>B&B \u003Cbr> MYOPIC | MALMCS | [基于人类移动预测的动态公共资源分配](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3380986) | [Python](https:\u002F\u002Fgithub.com\u002Fsjruan\u002Fmalmcs) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsjruan\u002Fmalmcs?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsjruan\u002Fmalmcs?color=critical&style=social) | UbiComp 2020\n| 地点 | ETH \u003Cbr> 酒店 \u003Cbr> 大学 \u003Cbr> Zara1 \u003Cbr> Zara2 | Social-BiGAT | [Social-BiGAT：使用自行车GAN和图注意力网络进行多模态轨迹预测](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fd09bf41544a3365a46c9077ebb5e35c3-Abstract.html) | 无 | NeurIPS 2019\n| 地点 | Foursquare \u003Cbr> Gowalla | VANext | [通过变分注意力预测人类移动](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313610) | 无 | WWW 2019\n| 地点 | Flickr \u003Cbr> Foursquare \u003Cbr> Geolife | CATHI | [上下文感知的变分轨迹编码与人类移动推断](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313608) | 无 | WWW 2019\n| 地点 | ETH \u003Cbr> 酒店 \u003Cbr> 大学 \u003Cbr> Zara1 \u003Cbr> Zara2 | STGAT | [STGAT：建模时空交互以进行人类轨迹预测](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fhtml\u002FHuang_STGAT_Modeling_Spatial-Temporal_Interactions_for_Human_Trajectory_Prediction_ICCV_2019_paper.html) | [代码](https:\u002F\u002Fgithub.com\u002Fhuang-xx\u002FSTGAT) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) | ICCV 2019\n| 地点 | BaiduBJ | HST-LSTM | [HST-LSTM：一种用于位置预测的分层时空长短记忆网络](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F324) | [代码](https:\u002F\u002Fgithub.com\u002FLogan-Lin\u002FST-LSTM_Code) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLogan-Lin\u002FST-LSTM_Code?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLogan-Lin\u002FST-LSTM_Code?color=critical&style=social) | IJCAI\u003Cbr>2018\n| 地点 | Foursquare \u003Cbr> MobileAPP \u003Cbr> CellularSH | DeepMove | [DeepMove：用注意力循环网络预测人类移动](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3178876.3186058) | [代码](https:\u002F\u002Fgithub.com\u002Fvonfeng\u002FDeepMove) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvonfeng\u002FDeepMove?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvonfeng\u002FDeepMove?color=critical&style=social) | WWW 2018\n| 地点 | MORE | MORE | [github](https:\u002F\u002Fgithub.com\u002Fxuehaouwa\u002FAwesome-Trajectory-Prediction) | [Hao Xue](https:\u002F\u002Fgithub.com\u002Fxuehaouwa\u002FAwesome-Trajectory-Prediction) | MORE\n| 地点 | MORE | MORE | [https:\u002F\u002Fgithub.com\u002FPursueee\u002FTrajectory-Paper-Collation](https:\u002F\u002Fgithub.com\u002FPursueee\u002FTrajectory-Paper-Collation) | [代码](https:\u002F\u002Fgithub.com\u002FPursueee\u002FTrajectory-Paper-Collation) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPursueee\u002FTrajectory-Paper-Collation?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FPursueee\u002FTrajectory-Paper-Collation?color=critical&style=social) | MORE\n\n\u003C!--\n| 地点 | Foursquare \u003Cbr> 移动APP \u003Cbr> CellularSH | DeepMove | [DeepMove：基于注意力循环网络的人类移动性预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3178876.3186058) | [代码](https:\u002F\u002Fgithub.com\u002Fvonfeng\u002FDeepMove) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvonfeng\u002FDeepMove?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fvonfeng\u002FDeepMove?color=critical&style=social) | WWW 2018\n\n| 地点 | ETH-UCY \u003Cbr> 碰撞 \u003Cbr> NGsim \u003Cbr>收费 \u003Cbr> NBA | FQA | [用于个性化下一站推荐的注意力循环神经网络](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5337) | [代码](https:\u002F\u002Fgithub.com\u002Fhuang-xx\u002FSTGAT) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fhuang-xx\u002FSTGAT?color=critical&style=social) | AAAI\u003Cbr>2020 -->\n\n# [事件预测](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表时间 |\n| :-: | :-: | :-: | :-: | :-: | - |\n| 论文数量：21 | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| 事件 | ETT \u003Cbr> PM2.5 \u003Cbr> IndD | NsTKA | [非平稳时间感知核化注意力用于时间序列事件预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539470) | [未来](https:\u002F\u002Fgithub.com\u002Falipay\u002Fnstka-kdd22) | KDD\u003Cbr>2022\n| 犯罪预测 | 芝加哥犯罪\u003Cbr> LA犯罪\u003Cbr> | HAGEN | [HAGEN：一种同质性感知的图卷积循环网络用于犯罪预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F20338) | [代码](https:\u002F\u002Fgithub.com\u002FRafa-zy\u002FHAGEN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRafa-zy\u002FHAGEN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRafa-zy\u002FHAGEN?color=critical&style=social) | AAAI\u003Cbr>2022\n| 事件 | PEMS | AGWN | [基于单帧观测的交通事故影响早期预测（学生摘要）](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_sa103) | [代码](https:\u002F\u002Fgithub.com\u002Fgm3g11\u002FAGWN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgm3g11\u002FAGWN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgm3g11\u002FAGWN?color=critical&style=social) | AAAI\u003Cbr>2022\n| 事件 | SLA-VAE \u003Cbr> 电商 | RETE | [RETE：基于统一查询产品演化图的检索增强型时间序列事件预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3511974) | [代码](https:\u002F\u002Fgithub.com\u002FDiMarzioBian\u002FRETE_TheWebConf) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDiMarzioBian\u002FRETE_TheWebConf?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FDiMarzioBian\u002FRETE_TheWebConf?color=critical&style=social) | WWW 2022\n| 事件 | NYC \u003Cbr> 芝加哥 | GSNet | [GSNet：从地理和语义方面学习时空相关性以预测交通事故风险](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16566) | [代码](https:\u002F\u002Fgithub.com\u002FEchohhhhhh\u002FGSNet) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FEchohhhhhh\u002FGSNet?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FEchohhhhhh\u002FGSNet?color=critical&style=social) | AAAI\u003Cbr>2021\n| 事件 | NYCIncidents \u003Cbr> CHIIncidents \u003Cbr> SFIncidents | STCGNN | [用于细粒度多事件协同预测的时空类别图神经网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482482) | [代码](https:\u002F\u002Fgithub.com\u002Funderdoc-wang\u002FSTC-GNN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Funderdoc-wang\u002FSTC-GNN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Funderdoc-wang\u002FSTC-GNN?color=critical&style=social) | CIKM\u003Cbr>2021\n| 事件 | 泰国 \u003Cbr> 埃及 \u003Cbr> India \u003Cbr>俄罗斯 \u003Cbr> Covid-19 | CMF | [通过情境化的多级特征学习理解事件预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482309) | 无 | CIKM\u003Cbr>2021\n| 事件预测 | DJIA30 \u003Cbr> WebTraffic \u003Cbr> NetFlow \u003Cbr> ClockErr \u003Cbr> AbServe | EvoNet | [基于进化状态图的时间序列事件预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3437963.3441827) | [tf](https:\u002F\u002Fgithub.com\u002FVachelHU\u002FEvoNet) | WSDM 2021\n| 事件 | NYCIncidents \u003Cbr> CHIIncidents \u003Cbr> SFIncidents | PreView | [用于实时事件预测的动态异构图神经网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403373) | 无 | KDD\u003Cbr>2020\n| 事件预测 | MIMIC-III | DSSM | [用于相关事件发生时间预测的深度状态空间生成模型](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403206) | 无 | KDD\u003Cbr>2020\n| 事件 | 北京 \u003Cbr> 苏州 \u003Cbr> 沈阳 | RiskOracle | [RiskOracle：一个分钟级的城市范围交通事故预测框架](https:\u002F\u002Fojs.aaai.org\u002F\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5480) | [TF](https:\u002F\u002Fgithub.com\u002Fzzyy0929\u002FAAAI2020-RiskOracle\u002F) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzzyy0929\u002FAAAI2020-RiskOracle\u002F?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzzyy0929\u002FAAAI2020-RiskOracle\u002F?color=critical&style=social) | AAAI\u003Cbr>2020\n| 事件 | NYCIncidents \u003Cbr> CHIIncidents | STrans | [用于细粒度空间事件预测的分层结构化Transformer网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380296) | 无 | WWW 2020\n| 事件 | 少量事件 | DMB-PN | [基于动态内存原型网络的元学习用于少样本事件检测](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3336191.3371796) | [数据集](https:\u002F\u002Fgithub.com\u002F231sm\u002FLow_Resource_KBP) | WSDM 2020\n| 事件 | NYC \u003Cbr> SIP | RiskSeq | [预见城市稀疏交通事故：一种时空多粒度视角](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9242313) | 无| TKDE 2020\n| 事件 | MemeTracker \u003Cbr> Weibo | LANTERN | [通过高效采样从高维事件序列中学习潜在过程](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fa29d1598024f9e87beab4b98411d48ce-Abstract.html) | [代码](https:\u002F\u002Fgithub.com\u002Fzhangzx-sjtu\u002FLANTERN-NeurIPS-2019) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhangzx-sjtu\u002FLANTERN-NeurIPS-2019?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhangzx-sjtu\u002FLANTERN-NeurIPS-2019?color=critical&style=social) | NeurIPS 2019\n| 事件 | Graph \u003Cbr> Stack \u003Cbr> SmartHome \u003Cbr> CarIndicators | WGP-LN, \u003Cbr> FD-Dir | [异步时间事件预测中的不确定性](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F78efce208a5242729d222e7e6e3e565e-Abstract.html) | [TF](https:\u002F\u002Fgithub.com\u002Fsharpenb\u002FUncertainty-Event-Prediction) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsharpenb\u002FUncertainty-Event-Prediction?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fsharpenb\u002FUncertainty-Event-Prediction?color=critical&style=social) | NeurIPS 2019\n| 事件 | 泰国 \u003Cbr> 埃及 \u003Cbr> India \u003Cbr>俄罗斯 | DynamicGCN | [学习动态上下文图以预测社交事件](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330919) | [代码](https:\u002F\u002Fgithub.com\u002Famy-deng\u002FDynamicGCN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) | KDD\u003Cbr>2019\n| 事件 | NYCCollision \u003Cbr> ChicagoCrime \u003Cbr> NYCTaxi | DMPP | [深度混合点过程：具有丰富上下文信息的时空事件预测](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330937) | 无 | KDD\u003Cbr>2019\n| 事件 | Civil \u003Cbr> Air Quality | SIMDA | [不完全标签多任务深度学习用于时空事件子类型预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4245) | 无 | AAAI\u003Cbr>2019\n| 犯罪预测 | NYC Crime \u003Cbr> NYC Anomaly \u003Cbr> Chicago Crime | MiST | [MiST：一个多视角、多模态的时空学习框架用于城市范围异常事件预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313730) | 无 | WWW 2019\n| 事件 | NYCAccident \u003Cbr> NYCEvent | DFN | [用于交通事故预测的深度动态融合网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357829) | 无 | CIKM\u003Cbr>2019\n| 事件 | | Hetero-ConvLSTM | [Hetero-ConvLSTM：一种基于深度学习的异构时空数据交通事故预测方法](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9242313) | 无| KDD\u003Cbr>2018\n\n\u003C!--\n| 活动 | 纽约事件 \u003Cbr> 芝加哥事件 | 预览 | [用于细粒度空间事件预测的层次结构Transformer网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380296) | [代码](https:\u002F\u002Fgithub.com\u002Famy-deng\u002FDynamicGCN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famy-deng\u002FDynamicGCN?color=critical&style=social) | WWW 2020 -->\n\n# [股票预测](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表时间 |\n| :-: | :-: | :-: | :-: | :-: | - |\n| 论文数量：30+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| 股票价格\u003Cbr>预测 | 纳斯达克 \u003Cbr> 纽约证券交易所 \u003Cbr> 标普500 | StockMixer | [StockMixer: 一种基于MLP的简单而强大的股票价格预测架构](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28681) | [代码](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FStockMixer) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FStockMixer?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FStockMixer?color=critical&style=social) | AAAI\u003Cbr>2024\n| 股票价格\u003Cbr>预测 | 中证300 \u003Cbr> 中证800 | MASTER | [MASTER: 市场引导的股票Transformer用于股票价格预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F27767) | [代码](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FMASTER) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FMASTER?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FMASTER?color=critical&style=social) | AAAI\u003Cbr>2024\n| 股票走势\u003Cbr>预测 | 秦 \u003Cbr> MAEC | ECHO-GL | [ECHO-GL: 受财报电话会议驱动的异构图学习用于股票走势预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F29305) | [代码](https:\u002F\u002Fgithub.com\u002Fpupu0302\u002FECHOGL) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fpupu0302\u002FECHOGL?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fpupu0302\u002FECHOGL?color=critical&style=social) | AAAI\u003Cbr>2024\n| 股票趋势\u003Cbr>预测 | 中证300 \u003Cbr> 中证500 | DoubleAdapt | [DoubleAdapt: 一种元学习方法用于股票趋势预测的增量学习](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3580305.3599315) | [代码](https:\u002F\u002Fgithub.com\u002FSJTU-Quant\u002FDoubleAdapt) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSJTU-Quant\u002FDoubleAdapt?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSJTU-Quant\u002FDoubleAdapt?color=critical&style=social) | KDD\u003Cbr>2023\n| 股票走势\u003Cbr>预测 | ACL18 \u003Cbr> 道琼斯工业平均指数 | PEN | [PEN: 预测-解释网络，用于以更好的可解释性预测股票价格走势](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F25648) | [TF](https:\u002F\u002Fgithub.com\u002FShuqi-li\u002FPEN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FShuqi-li\u002FPEN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FShuqi-li\u002FPEN?color=critical&style=social) | AAAI\u003Cbr>2023\n| 股票\u003Cbr>预测 | 纳斯达克 \u003Cbr> 纽约证券交易所 \u003Cbr> 中证 | RT-GCN | [基于关系时序图卷积网络的排名式股票预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10184655) | [代码](https:\u002F\u002Fgithub.com\u002Fzhengzetao\u002FRTGCN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhengzetao\u002FRTGCNt?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fzhengzetao\u002FRTGCN?color=critical&style=social) | ICDE 2023\n| 股票走势\u003Cbr>预测 | 标普500 | ESTIMATE | [在股票走势预测中高效整合多阶动力学与内部动力学](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570427) | [代码](https:\u002F\u002Fgithub.com\u002Fthanhtrunghuynh93\u002Festimate) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fthanhtrunghuynh93\u002Festimate?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fthanhtrunghuynh93\u002Festimate?color=critical&style=social) | WSDM 2023\n| 股票价格\u003Cbr>预测 | ACL18 | D-va | [扩散变分自编码器用于处理多步回归股票价格预测中的随机性](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614844) | [Gluonts](https:\u002F\u002Fgithub.com\u002Fkoa-fin\u002Fdva) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkoa-fin\u002Fdva?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fkoa-fin\u002Fdva?color=critical&style=social) | CIKM\u003Cbr>2023\n| 股票价格\u003Cbr>预测 | 中证300 \u003Cbr> 中证500 \u003Cbr> 中证800 | CISP | [顺应市场意志：一种上下文感知的漂移敏感型股票预测方法](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3583780.3614886) | 无 | CIKM\u003Cbr>2023\n| 股票走势\u003Cbr>预测 | 电话会议 | NumHTML | [NumHTML: 面向数值的层次化Transformer模型用于多任务金融预测](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai4799) | [Future,Author](https:\u002F\u002Fgithub.com\u002FYangLinyi) | AAAI\u003Cbr>2022\n| 股票预测 | 纳斯达克 \u003Cbr> 纽约证券交易所 \u003Cbr> 东京证券交易所 | ALSP-TF | [自适应长短模式Transformer用于股票投资选择](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F551) | 无 | IJCAI\u003Cbr>2022\n| 股票预测 | 标普500 \u003Cbr> A股&港交所 | HISN | [异构交互快照网络用于增强评论的股票画像与推荐](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F550) | 无 | IJCAI\u003Cbr>2022\n| 股票\u003Cbr>预测 | 标普500 \u003Cbr> 中证300 \u003Cbr> Twitter | THGNN | [用于金融时间序列预测的时序和异构图神经网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557089) | 无 | CIKM\u003Cbr>2022\n| 股票\u003Cbr>预测 | 中证800 | PASN | [用于学习股市交易模式的模式自适应专家网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557665) | 无 | CIKM\u003Cbr>2022\n| 股票走势\u003Cbr>预测 | 纳斯达克 \u003Cbr> 比特币 | KHIT | [基于核函数的混合可解释Transformer用于高频股票走势预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027785) | 无 | ICDM 2022\n| 股票走势\u003Cbr>预测 | 中证800 | TRA | [利用时序路由适配器和最优传输学习多种股票交易模式](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467358) | [代码](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks\u002FTRA) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks\u002FTRA?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks\u002FTRA?color=critical&style=social) | KDD\u003Cbr>2021\n| 股票走势\u003Cbr>预测 | ACL18 \u003Cbr> KDD17 \u003Cbr> NDX100 \u003Cbr> 中证300 \u003Cbr> 日经225\u003Cbr> FTSE100 | DTML | [通过具有多级上下文的数据轴Transformer实现精确的多元股票走势预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3447548.3467297) | 无| KDD\u003Cbr>2021\n| 股票 \u003Cbr>预测 | 自定义 | AD-GAT | [通过属性驱动的图注意力网络建模动量溢出效应进行股票预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16077) | [代码](https:\u002F\u002Fgithub.com\u002FRuichengFIC\u002FADGAT) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FRuichengFIC\u002FADGAT?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FRuichengFIC\u002FADGAT?color=critical&style=social) | AAAI\u003Cbr>2021\n| 股票选择 | 纳斯达克 \u003Cbr> 纽约证券交易所 \u003Cbr> 东京证券交易所| STHAN-SR | [通过时空超图注意力网络进行股票选择：一种排序学习方法](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16127) | 无 | AAAI\u003Cbr>2021\n| 股票走势\u003Cbr>预测 | TPX500 | CGM | [长期、短期和突发事件：基于图的多视角建模进行交易量走势预测](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0518.pdf) | [代码](https:\u002F\u002Fgithub.com\u002Flancopku\u002FCGM) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flancopku\u002FCGM?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flancopku\u002FCGM?color=critical&style=social) | IJCAI\u003Cbr>2021\n| 股票趋势\u003Cbr>预测 | 中证300 \u003Cbr> SPX \u003Cbr> TOPIX-100 | HATR | [用于股票趋势预测的层次化自适应时空关系建模](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0508.pdf) | 无 | IJCAI\u003Cbr>2021\n| 股票走势\u003Cbr>预测 | 纳斯达克 \u003Cbr> 纽约证券交易所 \u003Cbr> 东京证券交易所 \u003Cbr> 中国及香港 | HyperStockGAT | [利用时序路由适配器和最优传输学习多种股票交易模式](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450095) | 无| WWW 2021\n| 股票趋势\u003Cbr>预测 | 中证300 \u003Cbr> 中证500 | REST | [REST: 关系事件驱动的股票趋势预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450032) | 无 | WWW 2021\n| 股票趋势\u003Cbr>预测 | 中证300 \u003Cbr> 中证800 \u003Cbr> 纳斯达克100| CMLF | [使用多粒度数据进行股票趋势预测：一种对比学习与自适应融合的方法](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482483) | [代码](https:\u002F\u002Fgithub.com\u002FCMLF-git-dev\u002FCMLF) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCMLF-git-dev\u002FCMLF?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCMLF-git-dev\u002FCMLF?color=critical&style=social) | CIKM\u003Cbr>2021\n| 股票走势\u003Cbr>预测 | 自定义 | MFN | [将专家投资意见信号融入股票预测：一种深度学习框架](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5445) | 无 | AAAI\u003Cbr>2020\n| 股票走势\u003Cbr>预测 | TPX500 \u003Cbr> TPX100 | LSTM-RGCN | [利用图网络建模股票关系进行隔夜股票走势预测](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0626.pdf) | [代码](https:\u002F\u002Fgithub.com\u002Fliweitj47\u002Fovernight-stock-movement-prediction) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliweitj47\u002Fovernight-stock-movement-prediction?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fliweitj47\u002Fovernight-stock-movement-prediction?color=critical&style=social) | IJCAI\u003Cbr>2020\n| 股票走势\u003Cbr>预测 | 纳斯达克 \u003Cbr> 中国A股 | HMG-TF | [用于股票走势预测的层次化多尺度高斯Transformer](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0640.pdf) | 无 | IJCAI\u003Cbr>2020\n| 股票趋势\u003Cbr>预测 | FI-2010 \u003Cbr> CSI-2016 | MTDNN | [用于股票趋势预测的多尺度双向深层神经网络](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0628.pdf) | [Future](https:\u002F\u002Fgithub.com\u002Fmarscrazy\u002FMTDNN) | IJCAI\u003Cbr>2020\n| 股票价格\u003Cbr>预测 | 自定义 | Dandelion | [用于金融预测的领域自适应多模态神经注意力网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380288) | [Sklearn](https:\u002F\u002Fgithub.com\u002FLeo02016\u002FDandelion) | WWW 2020\n| 股票波动率\u003Cbr>预测 | 电话会议 | HTML | [基于层次化Transformer的多任务学习用于波动率预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380128) | [代码](https:\u002F\u002Fgithub.com\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction?color=critical&style=social) | WWW 2020\n| 定量\u003Cbr>投资 | 自定义 | KGEEF | [基于知识图谱的事件嵌入框架用于金融定量投资](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3397271.3401427) | 无 | SIGIR 2020\n| 股票价格\u003Cbr>预测 | TAQ | GARCH-LSTM | [利用高频金融数据进行价格预测：一种结合技术指标的自回归循环神经网络模型](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3412738) | 无 | CIKM\u003Cbr>2020\n| 股票走势\u003Cbr>预测 | HATS | STHGCN | [用于股票走势预测的时空超图卷积网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338303) | [代码](https:\u002F\u002Fgithub.com\u002Fmidas-research\u002Fsthgcn-icdm) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmidas-research\u002Fsthgcn-icdm?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmidas-research\u002Fsthgcn-icdm?color=critical&style=social) | ICDM 2020\n| 股市\u003Cbr>预测 | 日经 | GNNs | [利用滚动窗口分析探索图神经网络进行股市预测](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.10660) | 无 | NeurIPS 2019\n| 股票趋势\u003Cbr>预测 | 中国股票 | IMTR | [投资行为能揭示内在：探索股票内在属性进行股票趋势预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330663) | 无| KDD\u003Cbr>2019\n| 股票走势\u003Cbr>预测 | 中证200 \u003Cbr> 中证300 \u003Cbr> 中证500 | RNN-MRFs | [用于股票价格走势预测的多任务递归神经网络和高阶马尔可夫随机场：多任务RNN和高阶MRFs用于股票价格分类](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330983) | 无 | KDD\u003Cbr>2019\n| 股票走势\u003Cbr>预测 | 自定义 | TTIO | [为所有人提供个性化指标：利用股票嵌入优化个股技术指标](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330833) | 无 | KDD\u003Cbr>2019\n| 股票走势\u003Cbr>预测 | ACL18 \u003Cbr> KDD17 \u003Cbr> NDX100 \u003Cbr> 中证300 \u003Cbr> 日经225\u003Cbr> FTSE100| Adv-ALSTM | [通过对抗训练提升股票走势预测](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0810.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Ffulifeng\u002FAdv-ALSTM) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffulifeng\u002FAdv-ALSTM?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ffulifeng\u002FAdv-ALSTM?color=critical&style=social) | IJCAI\u003Cbr>2019\n| 股票 预测 | 纳斯达克 \u003Cbr> 纽约证券交易所 | RSR | [用于股票预测的时空关系排序](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330833) | [TF](https:\u002F\u002Fgithub.com\u002Ffulifeng\u002FTemporal_Relational_Stock_Ranking) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffulifeng\u002FTemporal_Relational_Stock_Ranking?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ffulifeng\u002FTemporal_Relational_Stock_Ranking?color=critical&style=social) | TOIS 2019\n| 股票走势\u003Cbr>预测 | 自定义 | StockNet | [从推文和历史价格预测股票走势](https:\u002F\u002Faclanthology.org\u002FP18-1183) | [TF](https:\u002F\u002Fgithub.com\u002Fyumoxu\u002Fstocknet-code) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyumoxu\u002Fstocknet-code?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyumoxu\u002Fstocknet-code?color=critical&style=social) | ACL 2018\n| 股票趋势\u003Cbr>预测 | 自定义 | HAN | [倾听混沌的低语：一种面向新闻的深度学习框架用于股票趋势预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3159652.3159690) | [TF](https:\u002F\u002Fgithub.com\u002Fdonghyeonk\u002Fhan) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdonghyeonk\u002Fhan?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdonghyeonk\u002Fhan?color=critical&style=social) | WSDM 2018\n| 股票价格\u003Cbr>预测 | 自定义 | SFM | [通过发现多频交易模式进行股票价格预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3097983.3098117) | [Keras](https:\u002F\u002Fgithub.com\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction?color=critical&style=social) | KDD\u003Cbr>2017\n| 股票走势\u003Cbr>预测 | 纳斯达克 \u003Cbr> 纽约证券交易所 | KGEB-CNN | [基于知识驱动的事件嵌入进行股票预测](https:\u002F\u002Faclanthology.org\u002FC16-1201) | 无 | COLING 2016\n\n\n\n# [其他预测](#content)\n| 任务 | 数据 | 模型 | 论文 | 代码 | 发表 |\n| :-: | :-: | :-: | :-: | :-: | - |\n| 论文数量：40+ | \u003Cimg width=150\u002F> | \u003Cimg width=220\u002F> | | | \u003Cimg width=300\u002F> |\n| 水温\u003Cbr>预测 | 特拉华河\u003Cbr>流域 | SR-MTL | [极端事件时间序列数据的元迁移学习：应用于水温预测](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3583780.3614966) | 无 | CIKM\u003Cbr>2023\n| 电信\u003Cbr>流量\u003Cbr>预测 | 米兰(MI)\u003Cbr>特伦蒂诺(TN) | TMLM | [基于多任务学习的电信流量预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570440) | [作者](https:\u002F\u002Fgithub.com\u002Fgpxlcj) | WSDM 2022\n| 比特币\u003Cbr>波动性\u003Cbr>预测 | Twitter | D-TCN\t | [问“谁”，而非“什么”：利用Twitter数据预测比特币波动性](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3539597.3570387) | [TF](https:\u002F\u002Fgithub.com\u002Fmeakbiyik\u002Fask-who-not-what) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmeakbiyik\u002Fask-who-not-what?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fmeakbiyik\u002Fask-who-not-what?color=critical&style=social) | WSDM 2022\n| 评级\u003Cbr>迁移\u003Cbr>预测 | 自我 | META | [基于多任务设想Transformer的自编码器用于企业信用评级迁移的早期预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539098) | 无 | KDD\u003Cbr>2022\n| COVID-19\u003Cbr>预测 | 东京COVID-19 | SAB-GNN | [利用网络搜索和出行数据从社会意识中进行多波次COVID-19预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539172) | [代码](https:\u002F\u002Fgithub.com\u002FJiaweiXue\u002FMultiwaveCovidPrediction) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJiaweiXue\u002FMultiwaveCovidPrediction?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FJiaweiXue\u002FMultiwaveCovidPrediction?color=critical&style=social) | KDD\u003Cbr>2022\n| 服务\u003Cbr>时间\u003Cbr>预测 | DowBJ\u003Cbr>SubBJ | MetaSTP | [通过空间元学习预测配送任务的服务时间](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539027) | 无 | KDD\u003Cbr>2022\n| 医生\u003Cbr> burnout\u003Cbr>预测 | EHR\u003Cbr> burnout | HiPAL | [HiPAL：利用电子健康记录中的活动日志进行医生burnout预测的深度框架](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3534678.3539056) | [TF](https:\u002F\u002Fgithub.com\u002FHanyangLiu\u002FHiPAL) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHanyangLiu\u002FHiPAL?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHanyangLiu\u002FHiPAL?color=critical&style=social) | KDD\u003Cbr>2022\n| 作物产量\u003Cbr>预测 | 美国作物 | GNN-RNN | [一种结合地理空间与时间信息的GNN-RNN方法：应用于作物产量预测](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aisi6416) | 无 | AAAI\u003Cbr>2022\n| 流行病预测 | 全球\u003Cbr>美国州\u003Cbr>美国县 | CausalGNN | [CausalGNN：基于因果关系的时空图神经网络](https:\u002F\u002Faaai-2022虚拟主席网帖子_aisi6475) | 未来 | AAAI\u003Cbr>2022\n| 土壤湿度\u003Cbr>预测 | 西班牙\u003Cbr>美国 | DGLR | [通过图神经网络进行动态结构学习，以预测精准农业中的土壤湿度](https:\u002F\u002Fdoi.org\u002F10.24963\u002Fijcai.2022\u002F720) | [代码](https:\u002F\u002Fgithub.com\u002FAnoushkaVyas\u002FDGLR) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAnoushkaVyas\u002FDGLR?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAnoushkaVyas\u002FDGLR?color=critical&style=social) | IJCAI\u003Cbr>2022\n| 疾病预测 | 疾病\u003Cbr>肿瘤 | PopNet | [PopNet：具有数据延迟的实时人群级疾病预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512127) | [代码](https:\u002F\u002Fgithub.com\u002Fv1xerunt\u002FPopNet) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fv1xerunt\u002FPopNet?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fv1xerunt\u002FPopNet?color=critical&style=social) | WWW 2022\n| 假新闻检测 | Snop\u003Cbr>PolitiFact | GET | [基于图神经网络的证据感知假新闻检测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3485447.3512122) | [Keras](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FGET) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCRIPAC-DIG\u002FGET?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCRIPAC-DIG\u002FGET?color=critical&style=social) | WWW 2022\n| 犯罪预测 | 纽约市\u003Cbr>芝加哥 | ST-HSL | [用于犯罪预测的空间-时间超图自监督学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835423) | [代码](https:\u002F\u002Fgithub.com\u002FLZH-YS1998\u002FSTHSL) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLZH-YS1998\u002FSTHSL?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLZH-YS1998\u002FSTHSL?color=critical&style=social) | ICDE 2022\n| 受欢迎度\u003Cbr>预测 | WbTopic\u003Cbr>WbRepost\u003Cbr>Twitter | HERI-GCN | [使用HERI-GCN在多源级联中进行深度受欢迎度预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9835455) | [代码](https:\u002F\u002Fgithub.com\u002FLes1ie\u002FHERI-GCN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLes1ie\u002FHERI-GCN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLes1ie\u002FHERI-GCN?color=critical&style=social) | ICDE 2022\n| 停车定价 | SFMTA\u003Cbr>SDOT | 无 | [基于预测的一次性动态停车定价](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557421) | 无| CIKM\u003Cbr>2022\n| 未来引用 | APS\u003Cbr>AMiner | DGNI | [为未来引用预测建模动态异质图和节点重要性](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557398) | 无| CIKM\u003Cbr>2022\n| 大流行\u003Cbr>预测 | Large-MG | HiSTGNN | [用于大流行预测的层次化时空图神经网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557350) | 无| CIKM\u003Cbr>2022\n| 搜索流量\u003Cbr>预测 | M5\u003Cbr>FGSF\u003Cbr>SQTE | STARDOM | [STARDOM：语义感知的深度层次预测模型，用于搜索流量预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557102) | 无| CIKM\u003Cbr>2022\n| 犯罪预测 | 纽约市\u003Cbr>芝加哥 | LTFMs | [用于犯罪预测的局部感知时间FM](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557657) | 无| CIKM\u003Cbr>2022\n| 能源市场 | Nordpool | 无 | [基于图的能源市场时空模型](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3511808.3557530) | 无| CIKM\u003Cbr>2022\n| 去噪健康\u003Cbr>风险预测 | EHR | MedSkim | [MedSkim：通过筛选医疗索赔数据进行去噪健康风险预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027678) | [代码](https:\u002F\u002Fgithub.com\u002FSH-Src\u002FMedSkim) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSH-Src\u002FMedSkim?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FSH-Src\u002FMedSkim?color=critical&style=social) | ICDM 2022\n| 需求\u003Cbr>预测 | 电子商务\u003Cbr>M5 | Forchestra | [大规模集成学习框架用于需求预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027662) | [代码](https:\u002F\u002Fgithub.com\u002Fyoung-j-park\u002F22-ICDM-Forchestra) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyoung-j-park\u002F22-ICDM-Forchestra?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyoung-j-park\u002F22-ICDM-Forchestra?color=critical&style=social) | ICDM 2022\n| 跨境\u003Cbr>交通流\u003Cbr>预测 | 上海BIKE\u003Cbr>南京Bus\u003Cbr>海口DiDi | CCMHC | [利用层次相关性进行跨城市跨模式交通流预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027729) | [代码](https:\u002F\u002Fgithub.com\u002Fchenyan89\u002FCCMHC) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenyan89\u002FCCMHC?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fchenyan89\u002FCCMHC?color=critical&style=social) | ICDM 2022\n| 降水\u003Cbr>临近预报 | ERA5\u003Cbr>WeatherBench | SCC-ConvLSTM | [用于降水临近预报的时空上下文一致性网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027644) | [未来](https:\u002F\u002Fgithub.com\u002FEricKing19\u002FSCCN) | ICDM 2022\n| 跨境\u003Cbr>交通流\u003Cbr>预测 | 深圳\u003Cbr>HB\u003Cbr>成都\u003Cbr>西安 | Mest-GAN | [Mest-GAN：利用元时空生成对抗网络进行跨城市城市交通估计](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027789) | 无 | ICDM 2022\n| 跨境\u003Cbr>人类流动\u003Cbr>预测 | 休斯顿\u003Cbr>爱荷华城 | STORM-GAN | [STORM-GAN：时空元GAN，用于跨城市估计COVID-19对人类流动的影响](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027783) | [代码](https:\u002F\u002Fgithub.com\u002FBaoHan88\u002FSTROM-GAN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBaoHan88\u002FSTROM-GAN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FBaoHan88\u002FSTROM-GAN?color=critical&style=social) | ICDM 2022\n| 跨境\u003Cbr>交通流\u003Cbr>预测 | 深圳\u003Cbr>HB\u003Cbr>成都\u003Cbr>西安 | STrans-GAN | [STrans-GAN：可空间转移的城市交通估计生成对抗网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10027643) | 无 | ICDM 2022\n| 流失预测 | Beidian\u003Cbr>Epinions | CFChurn | [用于流失预测的反事实建模框架](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3488560.3498468) | [代码](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FCFChurn) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftsinghua-fib-lab\u002FCFChurn?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Ftsinghua-fib-lab\u002FCFChurn?color=critical&style=social) | WSDM 2022\n| 流媒体\u003Cbr>交通流 | PEMS03 | TrafficStream | [TrafficStream：基于图神经网络和持续学习的流媒体交通流预测框架](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F498\u002F) | [代码](https:\u002F\u002Fgithub.com\u002FAprLie\u002FTrafficStream) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAprLie\u002FTrafficStream?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAprLie\u002FTrafficStream?color=critical&style=social) | IJCAI\u003Cbr>2021\n| 犯罪\u003Cbr>预测 | 纽约市\u003Cbr>芝加哥 | ST-SHN | [用于犯罪预测的空间-时间顺序超图网络，具备动态多层关系学习能力](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0225.pdf) | [TF](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FST-SHN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fakaxlh\u002FST-SHN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fakaxlh\u002FST-SHN?color=critical&style=social) | IJCAI\u003Cbr>2021\n| 购买意向预测 | JD-e-commerce | CHTR | [利用卷积层次Transformer网络进行购买意向预测](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458836) | 无 | ICDE 2021\n| 受欢迎度预测 | Tmall | ATNN | [用于电商中新商品受欢迎度预测的对抗式双塔神经网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458869) | 无 | ICDE 2021\n| 职业生涯轨迹预测 | 公司\u003Cbr>职位 | TACTP | [用于职业生涯轨迹预测的可变间隔时间序列建模：深度协作视角](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3442381.3449959) | 无 | WWW 2021\n| 健康预测 | NASH\u003Cbr>AD | UNITE | [UNITE：利用多源数据进行不确定性驱动的健康风险预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3442381.3450087) | [代码](https:\u002F\u002Fgithub.com\u002FChacha-Chen\u002FUNITE) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChacha-Chen\u002FUNITE?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FChacha-Chen\u002FUNITE?color=critical&style=social) | WWW 2021\n| COVID-19预测 | JHUCSSE | HierST | [HierST：统一的层级化时空框架，用于COVID-19趋势预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3481927) | [代码](https:\u002F\u002Fgithub.com\u002Fdolphin-zs\u002FHierST) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdolphin-zs\u002FHierST?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdolphin-zs\u002FHierST?color=critical&style=social) | CIKM\u003Cbr>2021\n| 故障预测 | 水管\u003Cbr>下水道管 | FP | [利用GNN和时间故障序列对大型水管网络进行故障预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3481918) | 无 | CIKM\u003Cbr>2021\n| 论文发表预测 | CSJ\u003Cbr>CSC | VPALG | [VPALG：利用图神经网络进行论文发表预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3459637.3482490) | 无 | CIKM\u003Cbr>2021\n| 水质预测 | | PDE-DGN | [偏微分方程驱动的动态图网络，用于预测溪流水温](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9679188) | 无 | ICDM 2021\n| 风险预测 | COPD\u003Cbr>心力衰竭\u003Cbr>肾脏疾病 | HiTANet | [HiTANet：用于电子健康记录上风险预测的层次化时间感知注意力网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403107) | [代码](https:\u002F\u002Fgithub.com\u002FHiTANet2020\u002FHiTANet) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHiTANet2020\u002FHiTANet?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHiTANet2020\u002FHiTANet?color=critical&style=social) | KDD\u003Cbr>2020\n| 销售预测 | 匿名化数据 | CARNN | [基于注意力的多模态新产品销售时间序列预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403362) | [代码](https:\u002F\u002Fgithub.com\u002FHumaticsLAB\u002FAttentionBasedMultiModalRNN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHumaticsLAB\u002FAttentionBasedMultiModalRNN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FHumaticsLAB\u002FAttentionBasedMultiModalRNN?color=critical&style=social) | KDD\u003Cbr>2020\n| 经济预测 | IRS | AMCN | [利用开放移民数据进行区域经济预测的注意力多图卷积网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403273) | 无 | KDD\u003Cbr>2020\n| 食品需求 | Ele.me | OFCT | [按需食品配送的订单履行周期时间估算](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403307) | 无 | KDD\u003Cbr>2020\n| 停车预测 | 北京\u003Cbr>上海 | SHARE | [半监督层次递归图神经网络，用于全市停车可用性预测](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5471) | [代码](https:\u002F\u002Fgithub.com\u002FVvrep\u002FSHARE-parking_availability_prediction-Code) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVvrep\u002FSHARE-parking_availability_prediction-Code?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FVvrep\u002FSHARE-parking_availability_prediction-Code?color=critical&style=social) | AAAI\u003Cbr>2020\n| 死亡风险预测| MIMIC-III\u003Cbr>eICU | DATA-GRU | [DATA-GRU：用于不规则多变量时间序列的双注意力时间感知门控循环单元](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5440) | 无 | AAAI\u003Cbr>2020\n| 停车预测 | 宁波\u003Cbr>长沙 | PewLSTM | [PewLSTM：具有天气感知门控机制的周期性LSTM，用于停车行为预测](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F610) | [代码](https:\u002F\u002Fgithub.com\u002FNingxuanFeng\u002FPewLSTM) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNingxuanFeng\u002FPewLSTM?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FNingxuanFeng\u002FPewLSTM?color=critical&style=social) | IJCAI\u003Cbr>2020\n| 健康风险 预测 | MIMIC-III\u003Cbr>ESRD | StageNet | [StageNet：用于健康风险预测的阶段感知神经网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380136) | [代码](https:\u002F\u002Fgithub.com\u002Fv1xerunt\u002FStageNet) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fv1xerunt\u002FStageNet?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fv1xerunt\u002FStageNet?color=critical&style=social) | WWW 2020\n| 微视频受欢迎度预测 | Xigua | MMVED | [用于微视频受欢迎度预测的多模态变分编码解码框架](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380004) | [TF](https:\u002F\u002Fgithub.com\u002Fyaochenzhu\u002FMMVED) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyaochenzhu\u002FMMVED?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyaochenzhu\u002FMMVED?color=critical&style=social) | WWW 2020\n| 药物需求预测 | Wikipedia | | [利用维基百科浏览量预测药物需求：来自暗网市场的证据](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3366423.3380022) | 无 | WWW 2020\n| 流行病 预测 | IDWR\u003Cbr>CDC\u003Cbr>US-HHS | Cola-GNN | [Cola-GNN：基于跨地点注意力的图神经网络，用于长期ILI预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411975) | [代码](https:\u002F\u002Fgithub.com\u002Famy-deng\u002Fcolagnn) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Famy-deng\u002Fcolagnn?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Famy-deng\u002Fcolagnn?color=critical&style=social) | CIKM\u003Cbr>2020\n| 风险 预测 | 心力衰竭\u003Cbr>肾脏疾病\u003Cbr>痴呆 | LSAN | [LSAN：利用层次化注意力建模长期依赖和短期相关性，用于风险预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411864) | [代码](https:\u002F\u002Fgithub.com\u002Fdmmlprojs\u002Flsan) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdmmlprojs\u002Flsan?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdmmlprojs\u002Flsan?color=critical&style=social) | CIKM\u003Cbr>2020\n| 闪电 预测 | 闪电 | HSTN | [用于闪电预测的异质时空网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338411) | [未来](https:\u002F\u002Fgithub.com\u002Fgyla1993\u002FHSTN) | ICDM 2020\n| 疾病 预测 | mPower | RNNODE | [利用多模态不规则收集的纵向智能手机数据预测帕金森病](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338417) | 无 | ICDM 2020\n| 湍流 预测 | 湍流 | T^2-Net | [T^2-Net：用于湍流预测的半监督深度模型](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9338418) | 无 | ICDM 2020\n| 受欢迎度 预测 | 新浪微博 | CoupledGNN | [利用耦合图神经网络在社交平台上进行受欢迎度预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3336191.3371834) | [TF](https:\u002F\u002Fgithub.com\u002FCaoQi92\u002FCoupledGNN) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCaoQi92\u002FCoupledGNN?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FCaoQi92\u002FCoupledGNN?color=critical&style=social) | WSDM 2020\n| 职业流动性 预测 | 自我 | HCPNN | [用于职业流动性预测的层次化职业路径感知神经网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330969) | [Python](https:\u002F\u002Fgithub.com\u002Fqingxin-meng\u002Fhierarchical-career-path-aware-network) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fqingxin-meng\u002Fhierarchical-career-path-aware-network?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fqingxin-meng\u002Fhierarchical-career-path-aware-network?color=critical&style=social) | KDD\u003Cbr>2019\n| 闪电 预测 | 闪电 | LightNet | [LightNet：用于闪电预测的双重时空编码网络模型](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3292500.3330717) | [Keras](https:\u002F\u002Fgithub.com\u002Fgyla1993\u002FLightNet) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgyla1993\u002FLightNet?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fgyla1993\u002FLightNet?color=critical&style=social) | KDD\u003Cbr>2019\n| 诊断 预测 | MIMICIII | MNN | [MNN：用于诊断预测的多模态注意力神经网络](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F823) | 无 | IJCAI\u003Cbr>2019\n| 犯罪 预测 | CrimeCHI\u003Cbr>CrimeNYC | NN-CCRF | [基于神经网络的连续条件随机场，用于精细化犯罪预测](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F577) | 无 | IJCAI\u003Cbr>2019\n| 人才流动\u003Cbr>预测 | OPNs | ETF | [利用动态潜在因子模型进行大规模人才流动预测？](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3308558.3313525) | 无 | WWW 2019\n| 销售 预测 | 零食\u003Cbr>PG&U | DSF | [用于电子商务销售预测的深度神经框架](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357883) | 无 | CIKM\u003Cbr>2019\n| 负载 预测 | 充电站 | HCFN | [用于充电站负载预测的异构组件融合网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3358073) | 无 | CIKM\u003Cbr>2019\n| 死亡风险 预测 | PUB\u003Cbr>MIMIC-III | UA-CRNN | [UA-CRNN：用于死亡风险预测的不确定性感知卷积循环神经网络](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3357384.3357884) | 无 | CIKM\u003Cbr>2019\n| 房价 预测 | NYCHouse\u003Cbr>BJHouse | FTD_DenseNet | [用于城市亚区房价预测的综合模型：多源数据视角](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970751) | 无 | ICDM 2019\n| 水质预测 | | TC | [利用稀疏样本预测沃罗诺拉供水网络的水质](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8970721) | 无 | ICDM 2019\n\n\u003C!-- \n| 风险预测 | 心力衰竭 \u003Cbr> 肾脏疾病 \u003Cbr> 痴呆 | LSAN | [LSAN：利用层次化注意力建模长期依赖和短期相关性进行风险预测](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3340531.3411864) | [代码](https:\u002F\u002Fgithub.com\u002Fdmmlprojs\u002Flsan) \u003Cbr>![星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdmmlprojs\u002Flsan?color=critical&style=social) \u003Cbr>![叉子](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fdmmlprojs\u002Flsan?color=critical&style=social) | CIKM\u003Cbr>2020 -->\n\n\n\n\n# [会议](#content)\n\n❗ 强烈建议使用 [dblp](https:\u002F\u002Fdblp.uni-trier.de\u002F) 和 [Aminer](https:\u002F\u002Fwww.aminer.cn\u002Fconf)（中文）进行检索。\n\n一些其他有用的网站：\n- CCF会议截止日期：https:\u002F\u002Fccfddl.github.io\u002F\n- 会议之眼：https:\u002F\u002Fwww.conferenceeye.cn\u002F#\u002Flayout\u002Fhome\n- Call4Papers：http:\u002F\u002F123.57.137.208\u002Fccf\u002Fccf-8.jsp\n- 会议列表：http:\u002F\u002Fwww.conferencelist.info\u002Fupcoming.html\n- PMLR：https:\u002F\u002Fproceedings.mlr.press\u002F （包含ICML、AISTATS、ACML、UAI等）\n## 会议列表\n\n|会议 | 大致提交时间 |\n|:--|:--|\n| [IJCAI](#IJCAI) | 1月14日~2月15日 |\n| [ICML](#ICML) | 1月23日~2月24日 |\n| [KDD](#KDD) | 2月3日~2月17日 |\n| [CIKM](#CIKM) | 5月15日~5月26日 |\n| [NeurIPS](#NeurIPS)| 5月18日~6月5日 |\n| [ICDM](#ICDM) | 6月5日~6月17日 |\n| [WSDM](#WSDM) | 7月17日~8月16日 |\n| [AAAI](#AAAI) | 9月5日~9月15日 |\n| [ICLR](#ICLR) | 9月25日~10月27日|\n| [WWW](#WWW) | 10月14日~11月5日|\n| [ICDE-1](#ICDE) | 6月1日~7月21日 |\n| [ICDE-2](#ICDE) | 10月1日~11月17日|\n\n以上为近7年来各会议的大致投稿时间。\n\n## 会议（期刊）CCF等级\n\n|会议（期刊） | CCF等级 |\n|:--|:--|\n| ICML | A |\n| NeurIPS | A | \n| ICLR | 无，但属于顶级 |\n| KDD | A | \n| AAAI | A |\n| IJCAI | A | \n| ICDE | A |\n| WWW | A |\n| ACL | A |\n| INFOCOM | A |\n| SIGIR | A |\n| VLDB | A |\n| UbiComp | A |\n| TKDE | A |\n| TPAMI | A |\n| TOIS | A |\n| CIKM | B |\n| ICDM | B |\n| WSDM | B |\n| COLING | B |\n| TNNLS | B |\n| TITS | B |\n| AISTATS | C，但属于顶尖 |\n| ICPR | C |\n| 交通运输研究C辑 | SCI一区 |\n\n注意：AISTATS在CCF中属于C类，但在计算数学领域（如概率问题）处于顶尖水平。\n\n## ICML\n\n> 论文集页面 https:\u002F\u002Fproceedings.mlr.press\u002F\n> 官网 https:\u002F\u002Ficml.cc\n\n| 会议 | 来源 | 截止日期 | 通知日期 |\n| ---------- | ---------------------------------------------------------- | ---------- | ---------- |\n|ICML\u003Cbr>2022|https:\u002F\u002Ficml.cc\u002FConferences\u002F2022\u002FSchedule| 2022年1月27日 | |\n|ICML\u003Cbr>2021| [https:\u002F\u002Ficml.cc\u002FConferences\u002F2021\u002FSchedule](https:\u002F\u002Ficml.cc\u002FConferences\u002F2021\u002FSchedule)| | |\n| ICML\u003Cbr>2020 | [https:\u002F\u002Ficml.cc\u002FConferences\u002F2020\u002FSchedule](https:\u002F\u002Ficml.cc\u002FConferences\u002F2020\u002FSchedule) | | |\n| ICML\u003Cbr>2019 | [https:\u002F\u002Ficml.cc\u002FConferences\u002F2019\u002FSchedule](https:\u002F\u002Ficml.cc\u002FConferences\u002F2019\u002FSchedule) | | |\n\n## NeurIPS\n\n[所有链接](https:\u002F\u002Fpapers.NeurIPS.cc\u002F)\n\n## ICLR\n\n在openreview上查找：\n\n\n> 官网 https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\n\n| 会议 | 来源 | 截止日期 | 通知日期 |\n| ---------- | ---------------------------------------------------------- | ---------- | ---------- |\n|ICLR\u003Cbr>2022|https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2022\u002FConference|2021年10月6日|2022年1月24日|\n| ICLR\u003Cbr>2021 | [https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2021\u002FConference](https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2021\u002FConference) | | |\n| ICLR\u003Cbr>2020 | [https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2020\u002FConference](https:\u002F\u002Fopenreview.net\u002Fgroup?id=ICLR.cc\u002F2020\u002FConference) | | |\n\n## KDD\n\n> 格式：https:\u002F\u002Fwww.kdd.org\u002Fkdd20xx\u002Faccepted-papers\n\n| 会议 | 来源 | 截止日期 | 通知日期 |\n| ---------- | --------------------------------------------------- | ---------- | ---------- |\n|KDD-22|| 2022年2月10日 | 2022年5月19日 |\n|KDD-21| [链接](https:\u002F\u002Fkdd.org\u002Fkdd2021\u002Faccepted-papers)| | |\n| KDD-20 | [链接](https:\u002F\u002Fwww.kdd.org\u002Fkdd2020\u002Faccepted-papers) | | |\n| KDD-19 | [链接](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers) | | |\n| KDD-18 | [链接](https:\u002F\u002Fwww.kdd.org\u002Fkdd2018\u002Faccepted-papers) | | |\n| KDD-17 | [链接](https:\u002F\u002Fwww.kdd.org\u002Fkdd2017\u002Faccepted-papers) | | |\n\n\n## AAAI\n\n| 会议 | 来源 | 截止日期 | 通知日期 |\n| ---------- | ------------------------------------------------------------ | ----------------- | ----------------- |\n|AAAI-22|[链接](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-22\u002Fwp-content\u002Fuploads\u002F2021\u002F12\u002FAAAI-22_Accepted_Paper_List_Main_Technical_Track.pdf)|2021年9月8日|2021年11月29日|\n| AAAI-21 | [链接](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-21\u002Fwp-content\u002Fuploads\u002F2020\u002F12\u002FAAAI-21_Accepted-Paper-List.Main_.Technical.Track_.pdf) | | |\n| AAAI-20 | [链接](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-20\u002Fwp-content\u002Fuploads\u002F2020\u002F01\u002FAAAI-20-Accepted-Paper-List.pdf) | | |\n| AAAI-19 | [链接](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-19\u002Fwp-content\u002Fuploads\u002F2018\u002F11\u002FAAAI-19_Accepted_Papers.pdf) | | |\n| AAAI-18 | [链接](https:\u002F\u002Faaai.org\u002FConferences\u002FAAAI-18\u002Fwp-content\u002Fuploads\u002F2017\u002F12\u002FAAAI-18-Accepted-Paper-List.Web_.pdf) | | |\n| AAAI-17 | [链接](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2017\u002Faaai17accepted-papers.pdf) | | |\n| AAAI-16 | [链接](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2016\u002Faaai16accepted-papers.pdf) | | |\n| AAAI-15 | [链接](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2015\u002Fiaai15accepted-papers.pdf) | | |\n| AAAI-14 | [链接](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2014\u002Faaai14accepts.php) | | |\n| AAAI-13 | [链接](https:\u002F\u002Fwww.aaai.org\u002FConferences\u002FAAAI\u002F2013\u002Faaai13accepts.php) | | |\n\n## [IJCAI](https:\u002F\u002Fwww.ijcai.org\u002Fpast_proceedings)\n\n| 会议 | 来源 | 截止日期 | 通知日期 |\n| ---------- | ----------------------------------------------------------- | ---------- | ---------- |\n|IJCAI-22| [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2022\u002F) | |\n|IJCAI-21|[链接](https:\u002F\u002Fijcai-21.org\u002Fprogram-main-track\u002F)| | |\n| IJCAI-20 | [链接](http:\u002F\u002Fstatic.ijcai.org\u002F2020-accepted_papers.html) | | |\n| IJCAI-19 | [链接](https:\u002F\u002Fwww.ijcai19.org\u002Faccepted-papers.html) | | |\n| IJCAI-18 | [链接](https:\u002F\u002Fwww.ijcai-18.org\u002Faccepted-papers\u002Findex.html) | | |\n| IJCAI-17 | [链接](https:\u002F\u002Fijcai-17.org\u002Faccepted-papers.html) | | |\n| IJCAI-16 | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2016) | | |\n| IJCAI-15 | [链接](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2015) | | |\n| IJCAI-14 | 无 | | |\n\n\n## ICDE\n\nIEEE 数据工程国际会议\n\n[全部链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fxpl\u002Fconhome\u002F1000178\u002Fall-proceedings)\n\n## WWW\n\nTheWebConf\n\n| 会议 | 来源 | 截止日期 | 通知日期 |\n| ---------- | ---------------------------------------------------------- | ---------- | ---------- |\n|WWW-22| [链接](https:\u002F\u002Fwww2022.thewebconf.org\u002Faccepted-papers\u002F)| 2021-10-21 ... | 2022-01-13 ... |\n|WWW-21| [链接](https:\u002F\u002Fwww2021.thewebconf.org\u002Fprogram\u002Fpapers\u002F)| | |\n| WWW-20 | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fproceedings\u002F10.1145\u002F3366423) | | |\n| WWW-19 | [链接](https:\u002F\u002Fwww2019.thewebconf.org\u002Faccepted-papers) | | |\n| WWW-18 | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fproceedings\u002F10.5555\u002F3178876) | | |\n| WWW-17 | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fproceedings\u002F10.1145\u002F3308558) | | |\n\n\n## CIKM\n\n信息与知识管理会议\n\n[全部链接](https:\u002F\u002Fdl.acm.org\u002Fconference\u002Fcikm)\n\n\n## ICDM\n\nIEEE 数据挖掘国际会议\n\n[全部链接]([https:\u002F\u002Fdl.acm.org\u002Fconference\u002Fcikm](https:\u002F\u002Fieeexplore.ieee.org\u002Fxpl\u002Fconhome\u002F1000179\u002Fall-proceedings))\n\n\n## WSDM\n\nACM 网络搜索与数据挖掘\n\n[全部链接](https:\u002F\u002Fdl.acm.org\u002Fconference\u002Fwsdm)","# Time-Series-Works-Conferences 快速上手指南\n\n`Time-Series-Works-Conferences` 并非一个需要安装运行的软件库，而是一个**时间序列领域学术论文与代码资源的汇总清单**。它按任务（如预测、异常检测）和方法论分类，收录了包括 ICML、AAAI 等顶级会议的最新成果。\n\n本指南将帮助开发者快速利用该资源查找论文、获取代码及数据集。\n\n## 环境准备\n\n由于本项目主要是资源索引，无需特定的系统环境或复杂的依赖安装。你只需要：\n\n* **操作系统**：Windows \u002F macOS \u002F Linux 均可。\n* **基础工具**：\n * Web 浏览器（用于访问 GitHub 页面或论文链接）。\n * Git（可选，用于克隆仓库到本地浏览）。\n * Python 环境（仅当你决定运行列表中某个具体模型的代码时才需要，具体依赖需参考对应模型的 `README`）。\n\n## 安装步骤（获取资源）\n\n你可以选择在线浏览或克隆到本地。\n\n### 方式一：在线浏览（推荐）\n直接访问项目主页查看最新整理的表格和链接：\n* **GitHub 仓库**: [https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences](https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences)\n* **专属网页版** (排版更佳): [https:\u002F\u002Flixus7.github.io\u002FTime-Series-Works-Conferences\u002F](https:\u002F\u002Flixus7.github.io\u002FTime-Series-Works-Conferences\u002F)\n\n### 方式二：克隆到本地\n如果你希望离线查阅或贡献内容，可使用以下命令：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences.git\ncd Time-Series-Works-Conferences\n```\n\n> **提示**：国内用户若遇到克隆速度慢的问题，可使用国内镜像源加速：\n> ```bash\n> git clone https:\u002F\u002Fgitee.com\u002Fmirrors\u002FTime-Series-Works-Conferences.git\n> ```\n> *(注：若 Gitee 无同步镜像，建议使用上述 GitHub 链接配合代理或加速工具)*\n\n## 基本使用\n\n本项目的核心用法是**按需检索**。作者将资源按“任务类型”进行了分类。\n\n### 1. 查找特定任务的论文与代码\n在仓库首页或网页版中，找到你感兴趣的任务板块，例如 **Multivariat Time Series Forecasting** (多变量时间序列预测)。\n\n表格结构如下：\n| Task | Data | Model | Paper | Code | Publication |\n| :--- | :--- | :--- | :--- | :--- | :--- |\n| Multivariat | TimesNet | LightGTS | [Paper Link](...) | [Code Link](...) | ICML 2025 |\n\n* **Paper**: 点击链接跳转至 OpenReview 或 arXiv 阅读论文。\n* **Code**: 点击链接跳转至对应的 GitHub 仓库获取源码。\n* **Data**: 部分条目标注了推荐使用的数据集（如 `TimesNet`, `ECL`, `NYC` 等），通常链接指向 `Time-Series-Library` 或其他数据源。\n\n### 2. 获取论文全集（网盘下载）\n作者提供了整理好的论文合集，包含未在 GitHub 直接列出的资源，可通过以下链接下载（可能需要网络工具）：\n\n* **OneDrive**: [点击下载链接](https:\u002F\u002F1drv.ms\u002Fu\u002Fs!Au2cJRs-_u93lDbLrSDkDy8htv2V?e=ftuaXd)\n* **Google Drive**: [点击下载链接](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F17bILWdDxUrufRp3yilYfoU5VKywwS1g6?usp=sharing)\n\n### 3. 理解缩写术语\n在阅读表格中的 \"Model\" 或方法论描述时，若遇到缩写，可参考仓库内的术语表。常见缩写示例：\n\n| 全称 | 缩写 | 含义 |\n| :--- | :--- | :--- |\n| Transformer | Trans | 变压器模型\u002F注意力机制 |\n| Graph Convolutional Network | GCN | 图卷积网络 |\n| AutoRegression | AR | 自回归模型 (RNN, GRU, LSTM 等) |\n| Contrastive Learning | CL | 对比学习 |\n| Federated Learning | FL | 联邦学习 |\n\n### 4. 运行具体模型\n一旦通过本列表找到了感兴趣的模型（例如 `LightGTS`）：\n1. 点击 **Code** 列的链接进入该模型的独立仓库。\n2. 遵循该独立仓库的 `README` 进行环境配置（通常是 `pip install -r requirements.txt`）。\n3. 下载对应的数据集（通常在 **Data** 列有指引）。\n4. 运行训练或推理脚本。\n\n---\n*注：本项目持续更新中，若发现资源缺失或错误，建议在原仓库提交 Issue 或 Pull Request。*","某高校人工智能实验室的博士生正在撰写关于“长序列时间序列预测”的综述论文，并计划复现几篇顶会最新模型以验证其假设。\n\n### 没有 Time-Series-Works-Conferences 时\n- **文献检索如大海捞针**：需要在 NIPS、ICML、KDD 等十几个顶级会议的海量录用论文中手动筛选时间序列相关文章，耗时数周且极易遗漏关键成果。\n- **分类整理耗费心力**：找到的论文散落在不同年份和会议中，缺乏统一的“任务类型”或“方法论”标签，难以快速梳理出技术演进脉络。\n- **资源获取支离破碎**：许多论文的代码链接失效或未公开，需要逐个访问作者主页或发送邮件索取，严重拖慢复现实验的进度。\n- **前沿动态更新滞后**：无法实时掌握 AAAI 2025 或 ICML 2025 等最新会议的接收情况，导致综述内容可能在新论文发表时已过时。\n\n### 使用 Time-Series-Works-Conferences 后\n- **一站式精准定位**：直接按会议（如 ICLR, KDD）或任务类别查看已整理的顶会论文列表，几分钟内即可构建完整的领域知识图谱。\n- **结构化技术洞察**：利用其按“任务”和“方法论”分类的架构，迅速对比不同模型在长序列预测上的优劣，清晰把握技术迭代路径。\n- **代码与数据直达**：通过集成的 OneDrive 和 Google Drive 链接，直接获取经过验证的论文代码与数据集，将环境搭建和复现准备时间从几天缩短至几小时。\n- **同步最新科研前沿**：依托持续更新的 Backlog 机制（如追踪 AAAI2025），确保研究始终基于最新的顶会成果，显著提升论文的创新性和时效性。\n\nTime-Series-Works-Conferences 将原本需要数周的文献调研与资源收集工作压缩至数小时，让研究者能专注于核心算法创新而非繁琐的信息搜集。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flixus7_Time-Series-Works-Conferences_6dd525e2.png","lixus7","Du","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Flixus7_4b31ded7.jpg","Ph.D. Student in UNSW, Sydney","UNSW","Sydney, NSW","du.yin@unsw.edu.au",null,"https:\u002F\u002Fgithub.com\u002Flixus7",950,95,"2026-04-12T15:54:13","MIT",1,"","未说明",{"notes":89,"python":87,"dependencies":90},"该仓库是一个时间序列论文和会议的整理列表（Awesome List），并非可执行的软件工具或模型代码库，因此没有特定的运行环境、GPU、内存或依赖库需求。文中列出的代码链接指向各个独立论文的官方实现仓库，用户需参考具体子项目的文档以获取相应的环境配置信息。部分论文数据存储在 OneDrive 和 Google Drive 上，访问 Google Drive 可能需要 VPN。",[],[16,14],[93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"time-series","deep-learning","spatio-temporal","paper-list","traffic-prediction","spatio-temporal-prediction","spatio-temporal-data","spatio-temporal-modeling","location","travel-time-prediction","demand-forecasting","anomaly-detection","multivariate-timeseries","probabilistic-models","time-series-forecasting","time-series-prediction","time-series-imputation","accident-detection",4,"2026-03-27T02:49:30.150509","2026-04-13T17:04:39.655647",[115,120,125,130,135,140],{"id":116,"question_zh":117,"answer_zh":118,"source_url":119},9670,"STGNN 模型是如何工作的？","您可以参考 LMissher 的实现细节，项目地址为：https:\u002F\u002Fgithub.com\u002FLMissher\u002FSTGNN。该模型全称为“基于时空图神经网络的交通流预测”（Traffic Flow Prediction via Spatial Temporal Graph Neural Network）。","https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\u002F17",{"id":121,"question_zh":122,"answer_zh":123,"source_url":124},9671,"如何向该仓库推荐或添加新的论文？","维护者欢迎用户提交 Pull Request (PR) 来添加新论文，这样您可以成为可见的贡献者。如果您不方便提交 PR，也可以在 Issue 中提供论文标题、链接和代码链接，维护者会很乐意帮忙添加。","https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\u002F23",{"id":126,"question_zh":127,"answer_zh":128,"source_url":129},9672,"发现论文的代码链接失效、错误或需要更新怎么办？","您可以直接在 Issue 中提供正确的 GitHub 仓库链接，维护者确认后会立即更新。例如，对于 FuSAGNet、FluxEV 等论文，用户提供的正确链接均已被采纳并更新到项目中。","https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\u002F22",{"id":131,"question_zh":132,"answer_zh":133,"source_url":134},9673,"为什么某些提到的论文代码没有被收录到列表中？","部分论文虽然提供了代码，但其任务类型（如链接预测 Link forecasting、时序点过程 temporal point process、光流估计 optical flow estimation）不在本项目的收录范围内，因此未被添加。本项目主要聚焦于特定的时间序列任务。","https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\u002F18",{"id":136,"question_zh":137,"answer_zh":138,"source_url":139},9674,"数据集中存在名称不统一（如 BJTaxi 和 TaxiBJ）或描述模糊的问题如何处理？","维护者已确认数据集名称不统一（如 BJTaxi 即 TaxiBJ）及描述模糊（如 Weather 数据集来源不同）的问题。目前计划在未来时间充裕时进行统一处理，甚至考虑建立单独页面展示数据集详情。用户也可以直接提交 PR 帮助修正这些细节。","https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\u002F25",{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},9675,"CCF 排名信息在列表中重复出现，是否有优化计划？","是的，维护者同意将 CCF 排名信息从每篇出版物下移至“会议（Conferences）”标题下统一管理，以避免冗余并清晰展示会议的平均质量等级。用户可以通过提交 PR 来实现这一更改。","https:\u002F\u002Fgithub.com\u002Flixus7\u002FTime-Series-Works-Conferences\u002Fissues\u002F10",[]]