[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-qingsongedu--awesome-AI-for-time-series-papers":3,"tool-qingsongedu--awesome-AI-for-time-series-papers":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",143909,2,"2026-04-07T11:33:18",[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。",107888,"2026-04-06T11:32:50",[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},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],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":10,"last_commit_at":59,"category_tags":60,"status":17},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[35,15,13,14],{"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":72,"owner_website":79,"owner_url":80,"languages":78,"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":32,"oss_zip_url":78,"oss_zip_packed_at":78,"status":17,"created_at":113,"updated_at":114,"faqs":115,"releases":116},5047,"qingsongedu\u002Fawesome-AI-for-time-series-papers","awesome-AI-for-time-series-papers","A professional list of Papers, Tutorials, and Surveys on AI for Time Series in top AI conferences and journals.","awesome-AI-for-time-series-papers 是一个专为人工智能时间序列分析领域打造的高质量资源库。它系统性地汇集了发表在顶级 AI 会议（如 NeurIPS、ICML、KDD、AAAI 等）和权威期刊上的最新论文、教程及综述，涵盖时间序列、时空数据、事件数据等多个细分方向。\n\n在时间序列分析技术飞速迭代的背景下，研究人员往往面临文献分散、难以追踪最新成果的痛点。awesome-AI-for-time-series-papers 有效解决了这一难题，它不仅提供论文列表，还特别标注了附带代码实现的资源，极大降低了复现门槛。其最显著的特点是更新极为及时，一旦顶会录用名单公布，列表便会迅速同步，确保用户能第一时间获取前沿资讯。\n\n这份资源库非常适合从事相关领域的科研人员、算法工程师以及高校学生使用。无论是希望快速了解领域全貌的初学者，还是急需追踪最新 SOTA（当前最佳）模型的专业开发者，都能从中高效获取所需信息。通过分类清晰的目录结构，用户可以轻松按年份或会议查找特定文献，是深耕 AI 时间序列分析不可或缺的案头指南。","# AI for Time Series (AI4TS) Papers, Tutorials, and Surveys\n\n[![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re) \n![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-Welcome-green) \n![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)\n[![Visits Badge](https:\u002F\u002Fbadges.pufler.dev\u002Fvisits\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)](https:\u002F\u002Fbadges.pufler.dev\u002Fvisits\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)\n\u003C!-- ![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers) -->\n\nA professionally curated list of papers (with available code), tutorials, and surveys on recent **AI for Time Series Analysis (AI4TS)**, including Time Series, Spatio-Temporal Data, Event Data, Sequence Data, Temporal Point Processes, etc., at the **Top AI Conferences and Journals**, which is **updated ASAP (the earliest time)** once the accepted papers are announced in the corresponding top AI conferences\u002Fjournals. Hope this list would be helpful for researchers and engineers who are interested in AI for Time Series Analysis.\n\nThe top conferences including:\n- Machine Learning: NeurIPS, ICML, ICLR\n- Data Mining: KDD, WWW\n- Artificial Intelligence: AAAI, IJCAI\n- Data Management: SIGMOD, VLDB, ICDE\n- Misc (selected): AISTAT, CIKM, ICDM, WSDM, SIGIR, ICASSP, CVPR, ICCV, etc.\n\nThe top journals including (mainly for survey papers):\nCACM, PIEEE, TPAMI, TKDE, TNNLS, TITS, TIST, SPM, JMLR, JAIR, CSUR, DMKD, KAIS, IJF, arXiv(selected), etc.\n\nIf you find any missed resources (paper\u002Fcode) or errors, please feel free to open an issue or make a pull request. \n\nFor general **Recent AI Advances: Tutorials and Surveys in various areas (DL, ML, DM, CV, NLP, Speech, etc.)** at the **Top AI Conferences and Journals**, please check [This Repo](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Fawesome-AI-tutorials-surveys). \n\n## Main Recent Update Note\n- [Mar. 04, 2024] Add papers accepted by ICLR'24, AAAI'24, WWW'24!\n- [Jul. 05, 2023] Add papers accepted by KDD'23!\n- [Jun. 20, 2023] Add papers accepted by ICML'23!\n- [Feb. 07, 2023] Add papers accepted by ICLR'23 and AAAI'23!\n- [Sep. 18, 2022] Add papers accepted by NeurIPS'22!\n- [Jul. 14, 2022] Add papers accepted by KDD'22!\n- [Jun. 02, 2022] Add papers accepted by ICML'22, ICLR'22, AAAI'22, IJCAI'22!\n\n## Table of Contents\n- [AI4TS Tutorials and Surveys](#AI4TS-Tutorials-and-Surveys)\n  * [AI4TS Tutorials](#AI4TS-Tutorials)\n  * [AI4TS Surveys](#AI4TS-Surveys)\n\n- [AI4TS Papers 2024](#AI4TS-Papers-2024)\n  * [NeurIPS 2024](#NeurIPS-2024), [ICML 2024](#ICML-2024), [ICLR 2024](#ICLR-2024)\n  * [KDD 2024](#KDD-2024), [WWW 2024](#WWW-2024), [AAAI 2024](#AAAI-2024), [IJCAI 2024](#IJCAI-2024)\n  * [SIGMOD VLDB ICDE 2024](#SIGMOD-VLDB-ICDE-2024)\n  * [Misc 2024](#Misc-2024)\n \n- [AI4TS Papers 2023](#AI4TS-Papers-2023)\n  * [NeurIPS 2023](#NeurIPS-2023), [ICML 2023](#ICML-2023), [ICLR 2023](#ICLR-2023)\n  * [KDD 2023](#KDD-2023), [AAAI 2023](#AAAI-2023), [IJCAI 2023](#IJCAI-2023)\n  * [SIGMOD VLDB ICDE 2023](#SIGMOD-VLDB-ICDE-2023)\n  * [Misc 2023](#Misc-2023)\n\n- [AI4TS Papers 2022](#AI4TS-Papers-2022)\n  * [NeurIPS 2022](#NeurIPS-2022), [ICML 2022](#ICML-2022), [ICLR 2022](#ICLR-2022)\n  * [KDD 2022](#KDD-2022), [AAAI 2022](#AAAI-2022), [IJCAI 2022](#IJCAI-2022)\n  * [SIGMOD VLDB ICDE 2022](#SIGMOD-VLDB-ICDE-2022)\n  * [Misc 2022](#Misc-2022)\n \n- [AI4TS Papers 2021](#AI4TS-Papers-2021)\n  * [NeurIPS 2021](#NeurIPS-2021), [ICML 2021](#ICML-2021), [ICLR 2021](#ICLR-2021)\n  * [KDD 2021](#KDD-2021), [AAAI 2021](#AAAI-2021), [IJCAI 2021](#IJCAI-2021)\n  * [SIGMOD VLDB ICDE 2021](#SIGMOD-VLDB-ICDE-2021)\n  * [Misc 2021](#Misc-2021)\n\n- [AI4TS Papers 201X-2020 Selected](#AI4TS-Papers-201X-2020-Selected)\n  * [NeurIPS 201X-2020](#NeurIPS-201X-2020), [ICML 201X-2020](#ICML-201X-2020), [ICLR 201X-2020](#ICLR-201X-2020)\n  * [KDD 201X-2020](#KDD-201X-2020), [AAAI 201X-2020](#AAAI-201X-2020), [IJCAI 201X-2020](#IJCAI-201X-2020)\n  * [SIGMOD VLDB ICDE 201X-2020](#SIGMOD-VLDB-ICDE-201X-2020)\n  * [Misc 201X-2020](#Misc-201X-2020)\n\n\n## AI4TS Tutorials and Surveys\n### AI4TS Tutorials\n* Out-of-Distribution Generalization in Time Series, in *AAAI* 2024. [\\[Link\\]](https:\u002F\u002Food-timeseries.github.io\u002F)\n* Robust Time Series Analysis and Applications: An Interdisciplinary Approach, in *ICDM* 2023. [\\[Link\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Ftimeseries-tutorial-icdm2023)\n* Robust Time Series Analysis and Applications: An Industrial Perspective, in *KDD* 2022. [\\[Link\\]](https:\u002F\u002Fqingsongedu.github.io\u002Ftimeseries-tutorial-kdd-2022\u002F)\n* Time Series in Healthcare: Challenges and Solutions, in *AAAI* 2022. [\\[Link\\]](https:\u002F\u002Fwww.vanderschaar-lab.com\u002Ftime-series-in-healthcare\u002F)\n* Time Series Anomaly Detection: Tools, Techniques and Tricks, in *DASFAA* 2022. [\\[Link\\]](https:\u002F\u002Fwww.dasfaa2022.org\u002F\u002Ftutorials\u002FTime%20Series%20Anomaly%20Result%20Master%20File_Dasfaa_2022.pdf)\n* Modern Aspects of Big Time Series Forecasting, in *IJCAI* 2021. [\\[Link\\]](https:\u002F\u002Flovvge.github.io\u002FForecasting-Tutorial-IJCAI-2021\u002F)\n* Explainable AI for Societal Event Predictions: Foundations, Methods, and Applications, in *AAAI* 2021. [\\[Link\\]](https:\u002F\u002Fyue-ning.github.io\u002Faaai-21-tutorial.html)\n* Physics-Guided AI for Large-Scale Spatiotemporal Data, in *KDD* 2021. [\\[Link\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fkdd2021tutorial\u002Fhome)\n* Deep Learning for Anomaly Detection, in *KDD & WSDM* 2020. [\\[Link1\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fkdd2020deepeye\u002Fhome) [\\[Link2\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fwsdm2020dlad) [\\[Link3\\]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Fn0qDbKL3UI)\n* Building Forecasting Solutions Using Open-Source and Azure Machine Learning, in *KDD* 2020. [\\[Link\\]](https:\u002F\u002Fchenhuims.github.io\u002Fforecasting\u002F)\n* Interpreting and Explaining Deep Neural Networks: A Perspective on Time Series Data, *KDD* 2020. [\\[Link\\]](https:\u002F\u002Fxai.kaist.ac.kr\u002FTutorial\u002F2020\u002F)\n* Forecasting Big Time Series: Theory and Practice, *KDD* 2019. [\\[Link\\]](https:\u002F\u002Flovvge.github.io\u002FForecasting-Tutorial-KDD-2019\u002F)\n* Spatio-Temporal Event Forecasting and Precursor Identification, *KDD* 2019. [\\[Link\\]](http:\u002F\u002Fmason.gmu.edu\u002F~lzhao9\u002Fprojects\u002Fevent_forecasting_tutorial_KDD)\n* Modeling and Applications for Temporal Point Processes, *KDD* 2019. [\\[Link1\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3332298) [\\[Link2\\]](https:\u002F\u002Fthinklab.sjtu.edu.cn\u002FTPP_Tutor_KDD19.html)\n\n\n### AI4TS Surveys\n#### General Time Series Survey\n* What Can Large Language Models Tell Us about Time Series Analysis, in *arXiv* 2024. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.02713)\n* Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook, in *arXiv* 2023. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.10196) [\\[Website\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002FAwesome-TimeSeries-SpatioTemporal-LM-LLM)\n* Deep Learning for Multivariate Time Series Imputation: A Survey, in *arXiv* 2024. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.04059) [\\[Website\\]](https:\u002F\u002Fgithub.com\u002Fwenjiedu\u002Fawesome_imputation)\n* Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects, in *arXiv* 2023. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.10125) [\\[Website\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002FAwesome-SSL4TS)\n* A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection, in *arXiv* 2023. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03759) [\\[Website\\]](https:\u002F\u002Fgithub.com\u002FKimMeen\u002FAwesome-GNN4TS)\n* Transformers in Time Series: A Survey, in *IJCAI* 2023. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07125) [\\[GitHub Repo\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Ftime-series-transformers-review)\n* Time series data augmentation for deep learning: a survey, in *IJCAI* 2021. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12478)\n* Neural temporal point processes: a review, in *IJCAI* 2021. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.03528)\n* Causal inference for time series analysis: problems, methods and evaluation, in *KAIS* 2022. [\\[paper\\]](https:\u002F\u002Fscholar.google.com\u002Fscholar?cluster=15831734748668637115&hl=en&as_sdt=5,48&sciodt=0,48)\n* Survey and Evaluation of Causal Discovery Methods for Time Series, in *JAIR* 2022. [\\[paper\\]](https:\u002F\u002Fwww.jair.org\u002Findex.php\u002Fjair\u002Farticle\u002Fview\u002F13428\u002F26775)\n* Deep learning for spatio-temporal data mining: A survey, in *TKDE* 2020. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04928)\n* Generative Adversarial Networks for Spatio-temporal Data: A Survey, in *TIST* 2022. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.08903)\n* Spatio-Temporal Data Mining: A Survey of Problems and Methods, in *CSUR* 2018. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3161602) \n* A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series, in *NeurIPS Workshop* 2020. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.00168)\n* Count Time-Series Analysis: A signal processing perspective, in *SPM* 2019. [\\[paper\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8700675)\n* Wavelet transform application for\u002Fin non-stationary time-series analysis: a review, in *Applied Sciences* 2019. [\\[paper\\]](https:\u002F\u002Fwww.mdpi.com\u002F2076-3417\u002F9\u002F7\u002F1345)\n* Granger Causality: A Review and Recent Advances, in *Annual Review of Statistics and Its Application* 2014. [\\[paper\\]](https:\u002F\u002Fwww.annualreviews.org\u002Fdoi\u002Fepdf\u002F10.1146\u002Fannurev-statistics-040120-010930)\n* A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data, in *arXiv* 2020. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.12493)\n* Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data, in *arXiv* 2022. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.02353)\n* A Survey on Time-Series Pre-Trained Models, in *arXiv* 2023. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.10716) [\\[link\\]](https:\u002F\u002Fgithub.com\u002Fqianlima-lab\u002Ftime-series-ptms)\n* Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects, in *arXiv* 2023. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.10125) [\\[Website\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002FAwesome-SSL4TS)\n* A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection, in *arXiv* 2023. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03759) [\\[Website\\]](https:\u002F\u002Fgithub.com\u002FKimMeen\u002FAwesome-GNN4TS)\n\n\n#### Time Series Forecasting Survey\n* Forecasting: theory and practice, in *IJF* 2022. [\\[paper\\]](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0169207021001758)\n* Time-series forecasting with deep learning: a survey, in *Philosophical Transactions of the Royal Society A* 2021. [\\[paper\\]](https:\u002F\u002Froyalsocietypublishing.org\u002Fdoi\u002Ffull\u002F10.1098\u002Frsta.2020.0209)\n* Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions, in *TITS* 2022. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.08555)\n* Event prediction in the big data era: A systematic survey, in *CSUR* 2022. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3450287)\n* A brief history of forecasting competitions, in *IJF* 2020. [\\[paper\\]](https:\u002F\u002Fwww.monash.edu\u002Fbusiness\u002Febs\u002Four-research\u002Fpublications\u002Febs\u002Fwp03-2019.pdf)\n* Neural forecasting: Introduction and literature overview, in *arXiv* 2020. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.10240) \n* Probabilistic forecasting, in *Annual Review of Statistics and Its Application* 2014. [\\[paper\\]](https:\u002F\u002Fwww.annualreviews.org\u002Fdoi\u002Fabs\u002F10.1146\u002Fannurev-statistics-062713-085831)\n\n#### Time Series Anomaly Detection Survey\n* A review on outlier\u002Fanomaly detection in time series data, in *CSUR* 2021. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.04236)\n* Anomaly detection for IoT time-series data: A survey, in *IEEE Internet of Things Journal* 2019. [\\[paper\\]](https:\u002F\u002Feprints.keele.ac.uk\u002F7576\u002F1\u002F08926446.pdf)\n* A Survey of AIOps Methods for Failure Management, in *TIST* 2021. [\\[paper\\]](https:\u002F\u002Fjorge-cardoso.github.io\u002Fpublications\u002FPapers\u002FJA-2021-025-Survey_AIOps_Methods_for_Failure_Management.pdf)\n* Sequential (quickest) change detection: Classical results and new directions, in *IEEE Journal on Selected Areas in Information Theory* 2021. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.04186)\n* Outlier detection for temporal data: A survey, TKDE'13. [\\[paper\\]](https:\u002F\u002Fromisatriawahono.net\u002Flecture\u002Frm\u002Fsurvey\u002Fmachine%20learning\u002FGupta%20-%20Outlier%20Detection%20for%20Temporal%20Data%20-%202014.pdf)\n* Anomaly detection for discrete sequences: A survey, TKDE'12. [\\[paper\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F5645624)\n* Anomaly detection: A survey, CSUR'09. [\\[paper\\]](https:\u002F\u002Farindam.cs.illinois.edu\u002Fpapers\u002F09\u002Fanomaly.pdf)\n \n#### Time Series Classification Survey\n* Deep learning for time series classification: a review, in *Data Mining and Knowledge Discovery* 2019. [\\[paper\\]](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10618-019-00619-1?sap-outbound-id=11FC28E054C1A9EB6F54F987D4B526A6EE3495FD&mkt-key=005056A5C6311EE999A3A1E864CDA986)\n* Approaches and Applications of Early Classification of Time Series: A Review, in *IEEE Transactions on Artificial Intelligence* 2020. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.02595)\n\n[\\[paper\\]]()\n## AI4TS Papers 2024\n### NeurIPS 2024\n\n### ICML 2024\n\n### ICLR 2024\n#### Time Series Forecasting\n* Time-LLM: Time Series Forecasting by Reprogramming Large Language Models [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Unb5CVPtae) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fkimmeen\u002Ftime-llm\u002F)\n* TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Tuh4nZVb0g) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fscxsunchenxi\u002Ftest)\n* TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=YH5w12OUuU)\n* DAM: A Foundation Model for Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4NhMhElWqP)\n* CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=MJksrOhurE) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fwxie9\u002Fcard)\n* Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=lJkOCMP2aW) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002Fpathformer)\n* iTransformer: Inverted Transformers Are Effective for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=JePfAI8fah) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002FiTransformer)\n* GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=c56TWtYp0W) \n* Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=qae04YACHs)\n* RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ltZ9ianMth) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fhaochenglouis\u002FRobustTSF)\n* ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU)\n* TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=7oLshfEIC2)\n* FITS: Modeling Time Series with 10k Parameters [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=bWcnvZ3qMb)\n* Multi-Resolution Diffusion Models for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=mmjnr0G8ZY)\n* MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=CZiY6OLktd)\n* Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=aFWUY3E7ws)\n* TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xtOydkE1Ku)\n* Towards Transparent Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=TYXtXLYHpR)\n* Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=O9nZCwdGcG)\n* Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=JiTVtCUOpS)\n* VQ-TR: Vector Quantized Attention for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=IxpTsFS7mh)\n* Copula Conformal prediction for multi-step time series prediction [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ojIJZDNIBj)\n* ClimODE: Climate Forecasting With Physics-informed Neural ODEs [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xuY33XhEGR)\n* STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=6iwg437CZs)\n* T-Rep: Representation Learning for Time Series using Time-Embeddings [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=3y2TfP966N)\n* Periodicity Decoupling Framework for Long-term Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=dp27P5HBBt)\n* Self-Supervised Contrastive Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=nBCuRzjqK7)\n\n#### Others  \n* Explaining Time Series via Contrastive and Locally Sparse Perturbations [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=qDdSRaOiyb) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fzichuan-liu\u002FContraLSP)\n* CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=iad1yyyGme) [\\[official code\\]](https:\u002F\u002Fwww.causaltime.cc\u002F)\n* SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=s9z0HzWJJp)\n* Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=CdjnzWsQax)\n* Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4VIgNuQ1pY)\n* Soft Contrastive Learning for Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=pAsQSWlDUf)\n* Retrieval-Based Reconstruction For Time-series Contrastive Learning [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=3zQo5oUvia)\n* Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=K2c04ulKXn)\n* Diffusion-TS: Interpretable Diffusion for General Time Series Generation [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4h1apFjO99)\n* Disentangling Time Series Representations via Contrastive based l-Variational Inference [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=iI7hZSczxE)\n* Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=9zhHVyLY4K)\n* Conditional Information Bottleneck Approach for Time Series Imputation [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=K1mcPiDdOJ)\n* Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=eY7sLb0dVF)\n* Learning to Embed Time Series Patches Independently [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WS7GuBDFa2)\n* Parametric Augmentation for Time Series Contrastive Learning [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=EIPLdFy3vp)\n* Inherently Interpretable Time Series Classification via Multiple Instance Learning [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xriGRsoAza)\n\n\n### KDD 2024\n\n### WWW 2024\n\n#### Time Series Forecasting\n* UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.09751)\n* Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.01231)\n\n#### Time Series Anomaly Detection\n* LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05668)\n* Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.02820)\n* Breaking the Time-Frequency Granularity Discrepancy in Time-Series Anomaly Detection [\\[paper\\]]()\n\n#### Others\n* Dynamic Multi-Network Mining of Tensor Time Series [\\[paper\\]]()\n* E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.14041)\n\n  \n### AAAI 2024\n#### Time Series Forecasting\n* U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.02236)\n* HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting [\\[paper\\]]()\n* Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting [\\[paper\\]]()\n* Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.08763)\n* MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.00423)\n* Latent Diffusion Transformer for Probabilistic Time Series Forecasting [\\[paper\\]]()\n* Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting [\\[paper\\]]()\n\n#### Time Series Classification, Clustering, Anomaly Detection\n* Graph-Aware Contrasting for Multivariate Time-Series Classification [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.05202)\n* Diffusion Language-Shapelets for Semisupervised Time-series Classification [\\[paper\\]]()\n*  Energy-efficient Streaming Time Series Classification with Attentive Power Iteration [\\[paper\\]]()\n* Cross-Domain Contrastive Learning for Time Series Clustering [\\[paper\\]]()\n* When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.11976)\n  \n#### Others\n* TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.15709)\n* GraFITi: Graphs for Forecasting Irregularly Sampled Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.12932)\n* IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.06741)\n* SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.05790)\n* CGS-Mask: Making Time Series Predictions Intuitive for All [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.09513)\n* CUTS+: High-dimensional Causal Discovery from Irregular Time-series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.05890)\n* Fully-Connected Spatial-Temporal Graph for Multivariate Time Series Data [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.05305)\n\n  \n## AI4TS Papers 2023\n### NeurIPS 2023\n#### Time Series Forecasting\n* OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71725)\n* One Fits All: Power General Time Series Analysis by Pretrained LM [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70856)\n* Large Language Models Are Zero Shot Time Series Forecasters [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70543)\n* BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69976)\n* ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71304)\n* FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71159)\n* Frequency-domain MLPs are More Effective Learners in Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70726)\n* Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72816)\n* WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69972)\n* Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70377)\n* Conformal PID Control for Time Series Prediction [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69896)\n* SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70829)\n* Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72562)\n\n#### Time Series Anomaly Detection, Classification\n* Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71195)\n* Nominality Score Conditioned Time Series Anomaly Detection by Point\u002FSequential Reconstruction [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70582)\n* MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71519)\n* Time Series as Images: Vision Transformer for Irregularly Sampled Time Series [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71219)\n* Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72608)\n  \n#### Others\n* Causal Discovery from Subsampled Time Series with Proxy Variables [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70936)\n* Causal Discovery in Semi-Stationary Time Series [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71016)\n* Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69958)\n* Sparse Deep Learning for Time Series Data: Theory and Applications [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72629)\n* CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70010)\n* WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F73593)\n* Conformal Prediction for Time Series with Modern Hopfield Networks [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72007)\n* Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71521)\n* On the Constrained Time-Series Generation Problem [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72006)\n* Contrast Everything: Multi-Granularity Representation Learning for Medical Time-Series [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70272)\n* Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71014)\n* FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70617)\n* BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series [\\[paper\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F73499\n\n### ICML 2023 \n#### Time Series Forecasting\n* Learning Deep Time-index Models for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=pgcfCCNQXO)\n* Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gTGFxnBymb) \n* Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=YbYMRZbO1Y) \n* Feature Programming for Multivariate Time Series Prediction [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=LVARH5wXM9) \n* Non-autoregressive Conditional Diffusion Models for Time Series Prediction [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=wZsnZkviro)\n  \n#### Time Series Anomaly Detection, Classification, Imputation, and XAI\n* Prototype-oriented unsupervised anomaly detection for multivariate time series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=3vO4lS6PuF) \n* Probabilistic Imputation for Time-series Classification with Missing Data [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=7pcZLgulIV) \n* Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=HRmSGZZ1FY) \n* Self-Interpretable Time Series Prediction with Counterfactual Explanations [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=JPMT9kjeJi) \n* Learning Perturbations to Explain Time Series Predictions [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WpeZu6WzTB)\n  \n#### Other Time Series Analysis\n* Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=OUWckW2g3j) \n* Neural Stochastic Differential Games for Time-series Analysis [\\[paper\\]]() \n* Sequential Monte Carlo Learning for Time Series Structure Discovery [\\[paper\\]]() \n* Context Consistency Regularization for Label Sparsity in Time Series [\\[paper\\]]() \n* Sequential Predictive Conformal Inference for Time Series [\\[paper\\]]() \n* Improved Online Conformal Prediction via Strongly Adaptive Online Learning [\\[paper\\]]() \n* Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series [\\[paper\\]]() \n* SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series [\\[paper\\]]() \n* Domain Adaptation for Time Series Under Feature and Label Shifts [\\[paper\\]]() \n* Deep Latent State Space Models for Time-Series Generation [\\[paper\\]]() \n* Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series [\\[paper\\]]() \n* Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting [\\[paper\\]]() \n* Generalized Teacher Forcing for Learning Chaotic Dynamics [\\[paper\\]]() \n* Learning the Dynamics of Sparsely Observed Interacting Systems [\\[paper\\]]() \n* Markovian Gaussian Process Variational Autoencoders [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Z8QlQ207V6) \n* ClimaX: A foundation model for weather and climate [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=TowCaiz7Ui) \n\n\n### ICLR 2023\n#### Time Series Forecasting\n* A Time Series is Worth 64 Words: Long-term Forecasting with Transformers [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Jbdc0vTOcol) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fyuqinie98\u002FPatchTST)\n* Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=vSVLM2j9eie) [\\[official code\\]]()\n* Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=sCrnllCtjoE) [\\[official code\\]]()\n* MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=zt53IDUR1U) [\\[official code\\]]()\n* Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=7C9aRX2nBf2) [\\[official code\\]]()\n* Learning Fast and Slow for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=q-PbpHD3EOk) [\\[official code\\]]()\n* Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=kUmdmHxK5N) [\\[official code\\]]()\n* Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ctmLBs8lITa) [\\[official code\\]]()\n\n#### Time Series Anomaly Detection and Classification\n* Unsupervised Model Selection for Time Series Anomaly Detection [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gOZ_pKANaPW) [\\[official code\\]]()\n* Out-of-distribution Representation Learning for Time Series Classification [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gUZWOE42l6Q) [\\[official code\\]]()\n\n#### Other Time Series Analysis\n* Effectively Modeling Time Series with Simple Discrete State Spaces [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=2EpjkjzdCAa) [\\[official code\\]]()\n* TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis  [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ju_Uqw384Oq) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library)\n* Contrastive Learning for Unsupervised Domain Adaptation of Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xPkJYRsQGM) [\\[official code\\]]()\n* Recursive Time Series Data Augmentation [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=5lgD4vU-l24s) [\\[official code\\]]()\n* Multivariate Time-series Imputation with Disentangled Temporal Representations [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=rdjeCNUS6TG) [\\[official code\\]]()\n* Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=UClBPxIZqnY) [\\[official code\\]]()\n* Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=i_1rbq8yFWC) [\\[official code\\]]()\n* CUTS: Neural Causal Discovery from Unstructured Time-Series Data [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=UG8bQcD3Emv) [\\[official code\\]]()\n* Temporal Dependencies in Feature Importance for Time Series Prediction [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=C0q9oBc3n4) [\\[official code\\]]()\n\n### KDD 2023\n#### Time Series Anomaly Detection\n* DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.10347) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FKDD2023-DCdetector)\n* Imputation-based Time-Series Anomaly Detection with Conditional Weight-Incremental Diffusion Models [\\[paper\\]](https:\u002F\u002Fgithub.com\u002FChunjingXiao\u002FDiffAD\u002Fblob\u002Fmain\u002FKDD_23_DiffAD.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FChunjingXiao\u002FDiffAD)\n* Precursor-of-Anomaly Detection for Irregular Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.15489)  \n#### Time Series Forecasting\n* When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting\n* TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.09364)\n* Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting\n* Sparse Binary Transformers for Multivariate Time Series Modeling [\\[paper\\]]() [\\[official code\\]]()\n* Interactive Generalized Additive Model and Its Applications in Electric Load Forecasting\n#### Time Series Forecasting (Traffic)\n* Frigate: Frugal Spatio-temporal Forecasting on Road Networks [\\[paper\\]]() [\\[official code\\]]()\n* Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities\n* Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training\n* Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction\n#### Time Series Imputation\n* Source-Free Domain Adaptation with Temporal Imputation for Time Series Data [\\[paper\\]]() [\\[official code\\]]()\n* Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders\n* An Observed Value Consistent Diffusion Model for Imputing Missing Values in Multivariate Time Series\n#### Others\n* Online Few-Shot Time Series Classification for Aftershock Detection [\\[paper\\]]() [\\[official code\\]]()\n* Self-supervised Classification of Clinical Multivariate Time Series using Time Series Dynamics\n* Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series\n* Parameter-free Spikelet: Discovering Different Length and Warped Time Series Motifs using an Adaptive Time Series Representation\n* FLAMES2Graph: An Interpretable Federated Multivariate Time Series Classification Framework\n* WHEN: A Wavelet-DTW Hybrid Attention Network for Heterogeneous Time Series Analysis\n\n### AAAI 2023\n#### Time Series Forecasting\n* AirFormer: Predicting Nationwide Air Quality in China with Transformers [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.15979) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fyoshall\u002FAirFormer)\n* Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting [\\[paper\\]]() [\\[official code\\]]()\n* WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series [\\[paper\\]]() [\\[official code\\]]() \n* Are Transformers Effective for Time Series Forecasting [\\[paper\\]]() [\\[official code\\]]()\n* Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose [\\[paper\\]]() [\\[official code\\]]()\n* An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.15891) [\\[official code\\]]()\n* Spatio-Temporal Meta-Graph Learning for Traffic Forecasting [\\[paper\\]]() [\\[official code\\]]()\n\n#### Other Time Series Analysis\n* Temporal-Frequency Co-Training for Time Series Semi-Supervised Learning [\\[paper\\]]() [\\[official code\\]]()\n* SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation [\\[paper\\]]() [\\[official code\\]]()\n* Causal Recurrent Variational Autoencoder for Medical Time Series Generation [\\[paper\\]]() [\\[official code\\]]()\n* AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-series Generation [\\[paper\\]]() [\\[official code\\]]()\n* SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series Classification [\\[paper\\]]() [\\[official code\\]]()\n\n\n## AI4TS Papers 2022\n### NeurIPS 2022\n#### Time Series Forecasting\n* FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.08897) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FNeurIPS2022-FiLM)\n* SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.09305) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fcure-lab\u002FSCINet)\n\n* Non-stationary Transformers: Rethinking the Stationarity in Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.14415)\n* Earthformer: Exploring Space-Time Transformers for Earth System Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.05833)\n* Generative Time Series Forecasting with Diffusion, Denoise and Disentanglement\n* Learning Latent Seasonal-Trend Representations for Time Series Forecasting\n* WaveBound: Dynamically Bounding Error for Stable Time Series Forecasting\n \n* Time Dimension Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting\n \n* Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks\n \n* C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting\n \n* Meta-Learning Dynamics Forecasting Using Task Inference [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.10271)\n \n* Conformal Prediction with Temporal Quantile Adjustments\n \n\n\n\n#### Other Time Series Analysis\n* Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency, [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.08496) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FTFC-pretraining)\n* Causal Disentanglement for Time Series\n* BILCO: An Efficient Algorithm for Joint Alignment of Time Series\n* Dynamic Sparse Network for Time Series Classification: Learning What to “See”\n* AutoST: Towards the Universal Modeling of Spatio-temporal Sequences\n \n* GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks\n \n* Efficient learning of nonlinear prediction models with time-series privileged information\n \n* Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models\n \n\n\n\n\n### ICML 2022\n#### Time Series Forecasting\n* FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.12740) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FICML2022-FEDformer)\n* TACTiS: Transformer-Attentional Copulas for Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.03528) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FServiceNow\u002Ftactis)\n* Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.06544) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fg-benton\u002Fvolt)\n* Domain Adaptation for Time Series Forecasting via Attention Sharing [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.06828) \n* DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Flan22a.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FSYLan2019\u002FDSTAGNN)\n\n#### Time Series Anomaly Detection\n* Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fchen22x.html)\n\n#### Other Time Series Analysis\n* Adaptive Conformal Predictions for Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07282) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmzaffran\u002Fadaptiveconformalpredictionstimeseries)\n* Modeling Irregular Time Series with Continuous Recurrent Units [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.11344) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fboschresearch\u002Fcontinuous-recurrent-units)\n* Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.04770) \n* Reconstructing nonlinear dynamical systems from multi-modal time series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.02922) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fdurstewitzlab\u002Fmmplrnn)\n* Utilizing Expert Features for Contrastive Learning of Time-Series Representations [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.11517) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fboschresearch\u002Fexpclr)\n* Learning of Cluster-based Feature Importance for Electronic Health Record Time-series [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Faguiar22a.html)\n\n### ICLR 2022\n#### Time Series Forecasting\n* Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=0EXmFzUn5I) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Falipay\u002FPyraformer)\n* DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=AJAR-JgNw__) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fweifantt\u002Fdepts)\n* CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=PilZY3omXV2) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002FCoST)\n* Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=cGDAkQo1C0p) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fts-kim\u002FRevIN)\n* TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=wv6g8fWLX2q) [\\[official code\\]](https:\u002F\u002Fwww.dropbox.com\u002Fsh\u002Fn0ajd5l0tdeyb80\u002FAABGn-ejfV1YtRwjf_L0AOsNa?dl=0)\n* Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=L01Nn_VJ9i) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FBack2Future)\n* On the benefits of maximum likelihood estimation for Regression and Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=zrW-LVXj2k1)\n* Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=wwDg3bbYBIq) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fhyunwookl\u002Fpm-memnet)\n\n\n#### Time Series Anomaly Detection\n* Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=LzQQ89U1qm_) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002FAnomaly-Transformer)\n* Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=45L_dgP48Vd) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fenyandai\u002Fganf)\n\n#### Time Series Classification\n* T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=U4uFaLyg7PV)\n* Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=PDYs7Z2XFGv)\n\n#### Other Time Series Analysis\n* Graph-Guided Network for Irregularly Sampled Multivariate Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Kwm8I7dU-l5)\n* Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Az7opqbQE-3)\n* Transformer Embeddings of Irregularly Spaced Events and Their Participants [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Rty5g9imm7H)\n* Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=kOu3-S3wJ7)\n* PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Ix_mh42xq5w)\n* Huber Additive Models for Non-stationary Time Series Analysis [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=9kpuB2bgnim)\n* LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=fCG75wd39ze)\n* Imbedding Deep Neural Networks [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=yKIAXjkJc2F)\n* Coherence-based Label Propagation over Time Series for Accelerated Active Learning [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gjNcH0hj0LM)\n* Long Expressive Memory for Sequence Modeling [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=vwj6aUeocyf)\n* Autoregressive Quantile Flows for Predictive Uncertainty Estimation [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=z1-I6rOKv1S)\n* Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=HFmAukZ-k-2)\n* Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=p3DKPQ7uaAi)\n* Explaining Point Processes by Learning Interpretable Temporal Logic Rules [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=P07dq7iSAGr)\n\n\n### KDD 2022\n \n#### Time Series Forecasting\n* Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting [\\[code\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FKDD2022-Quatformer)\n* Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting\n* Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting\n* Multi-Variate Time Series Forecasting on Variable Subset\n* Greykite: Deploying Flexible Forecasting at Scale in LinkedIn\n\n#### Time Series Anomaly Detection\n* Local Evaluation of Time Series Anomaly Detection Algorithms\n* Scaling Time Series Anomaly Detection to Trillions of Datapoints and Ultra-fast Arriving Data Streams\n\n#### Other Time-Series\u002FSpatio-Temporal Analysis\n* Task-Aware Reconstruction for Time-Series Transformer\n* Towards Learning Disentangled Representations for Time Series\n* ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences\n* Non-stationary Time-aware Kernelized Attention for Temporal Event Prediction\n* MSDR: Multi-Step Dependency Relation Networks for Spatial Temporal Forecasting\n* Graph2Route: A Dynamic Spatial-Temporal Graph Neural Network for Pick-up and Delivery Route Prediction\n* Beyond Point Prediction: Capturing Zero-Inflated & Heavy-Tailed Spatiotemporal Data with Deep Extreme Mixture Models\n* Robust Event Forecasting with Spatiotemporal Confounder Learning\n* Mining Spatio-Temporal Relations via Self-Paced Graph Contrastive Learning\n* Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer\n* Characterizing Covid waves via spatio-temporal decomposition\n\n\n### AAAI 2022\n#### Time Series Forecasting\n* CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai7403) \n* Reinforcement Learning based Dynamic Model Combination for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai8424)\n* DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.04038) [official code\\]](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks_dynamic\u002FDDG-DA)\n* PrEF: Probabilistic Electricity Forecasting via Copula-Augmented State Space Model [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aisi7128)\n* LIMREF: Local Interpretable Model Agnostic Rule-Based Explanations for Forecasting, with an Application to\nElectricity Smart Meter Data [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aisi8802)  \n* Learning and Dynamical Models for Sub-Seasonal Climate Forecasting: Comparison and Collaboration [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.05196) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FSijie-umn\u002FSSF-MIP)\n* CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aisi6475)\n* Conditional Local Convolution for Spatio-Temporal Meteorological Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.01000) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fbird-tao\u002Fclcrn)\n* Graph Neural Controlled Differential Equations for Traffic Forecasting [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai6502) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FSTG-NCDE)\n* STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai211) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FEcho-Ji\u002FSTDEN)\n\n#### Time Series Anomaly Detection\n* Towards a Rigorous Evaluation of Time-Series Anomaly Detection [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai2239)  \n* AnomalyKiTS-Anomaly Detection Toolkit for Time Series [\\[Demo paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_dm318) \n\n#### Other Time Series Analysis\n* TS2Vec: Towards Universal Representation of Time Series [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai8809) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fyuezhihan\u002Fts2vec)\n* I-SEA: Importance Sampling and Expected Alignment-Based Deep Distance Metric Learning for Time Series Analysis and Embedding [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai10930)  \n* Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai4151)  \n* Conditional Loss and Deep Euler Scheme for Time Series Generation [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai12878)  \n* Clustering Interval-Censored Time-Series for Disease Phenotyping [\\[paper\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai12517)  \n\n\n### IJCAI 2022\n#### Time Series Forecasting\n* Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.13767)\n* Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.03394) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002Faggforecaster)\n* Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting\n* DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.02441) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fgalib19\u002Fdeepextrema-ijcai22-)\n* Memory Augmented State Space Model for Time Series Forecasting  \n* Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data \n* Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.11008) [\\[official code\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.11008)\n* FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting\n\n#### Time Series Anomaly Detection\n* Neural Contextual Anomaly Detection for Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.07702)  \n* GRELEN: Multivariate Time Series Anomaly Detection from the Perspective of Graph Relational Learning  \n\n#### Time Series Classification\n* A Reinforcement Learning-Informed Pattern Mining Framework for Multivariate Time Series Classification [\\[paper\\]](https:\u002F\u002Fcpsl.pratt.duke.edu\u002Fsites\u002Fcpsl.pratt.duke.edu\u002Ffiles\u002Fdocs\u002Fgao_ijcai22.pdf)\n* T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification\n\n\n### SIGMOD VLDB ICDE 2022\n#### Time Series Forecasting\n* METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting, VLDB'22. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp224-cui.pdf) [\\[official code\\]](https:\u002F\u002Fzheng-kai.com\u002Fcode\u002Fmetro_single_s.zip) \n* AutoCTS: Automated Correlated Time Series Forecasting, VLDB'22. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp971-wu.pdf)\n* Towards Spatio-Temporal Aware Traffic Time Series Forecasting, ICDE'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.15737) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002Fst-wa) \n\n\n#### Time Series Anomaly Detection\n* Sintel: A Machine Learning Framework to Extract Insights from Signals, SIGMOD'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.09108) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsarahmish\u002Fsintel-paper) \n* TSB-UAD: An End-to-End Benchmark Suite for Univariate Time-Series Anomaly Detection, VLDB'22. [\\[paper\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fpublications\u002Fpvldb22-tsbuad.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjohnpaparrizos\u002FTSB-UAD)\n* TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data, VLDB'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.07284) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fimperial-qore\u002Ftranad)\n* Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles, VLDB'22. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp611-chaves.pdf)\n* Robust and Explainable Autoencoders for Time Series Outlier Detection, ICDE'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.03341)\n* Anomaly Detection in Time Series with Robust Variational Quasi-Recurrent Autoencoders, ICDE'22.  \n\n#### Time Series Classification\n* IPS: Instance Profile for Shapelet Discovery for Time Series Classification, ICDE'22. [\\[paper\\]](https:\u002F\u002Fpersonal.ntu.edu.sg\u002Fassourav\u002Fpapers\u002FICDE-22-IPS.pdf)\n* Towards Backdoor Attack on Deep Learning based Time Series Classification, ICDE'22. [\\[paper\\]]()\n\n#### Other Time Series Analysis\n* OnlineSTL: Scaling Time Series Decomposition by 100x, VLDB'22. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp1417-mishra.pdf) \n* Efficient temporal pattern mining in big time series using mutual information, VLDB'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.03653)\n* Learning Evolvable Time-series Shapelets, ICDE'22.  \n\n\n\u003C!--  [\\[paper\\]]() [\\[official code\\]]()  -->  \n### Misc 2022\n#### Time Series Forecasting\n* CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting, WWW'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.07438) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fadityalab\u002Fcamul)\n* Multi-Granularity Residual Learning with Confidence Estimation for Time Series Prediction, WWW'22. [\\[paper\\]](https:\u002F\u002Fweb.archive.org\u002Fweb\u002F20220426115606id_\u002Fhttps:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3485447.3512056)  \n* RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph, WWW'22. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3485447.3511974) \n* Robust Probabilistic Time Series Forecasting, AISTATS'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.11910) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Ftetrzim\u002Frobust-probabilistic-forecasting) \n* Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting, AISTATS'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.06581)\n\n\n#### Time Series Anomaly Detection\n* TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis, CIKM'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.09693) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FCIKM22-TFAD)\n* Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection, AISTATS'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07586) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fcchallu\u002Fdghl)\n* A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems, WWW'22. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3485447.3511984) \n\n\n#### Other Time Series Analysis\n* Decoupling Local and Global Representations of Time Series, AISTATS'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.02262) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fgoogleinterns\u002Flocal_global_ts_representation)\n* LIMESegment: Meaningful, Realistic Time Series Explanations, AISTATS'22. [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv151\u002Fsivill22a.html)\n* Using time-series privileged information for provably efficient learning of prediction models, AISTATS'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.14993) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FRickardKarl\u002FLearningUsingPrivilegedTimeSeries)\n* Amortised Likelihood-free Inference for Expensive Time-series Simulators with Signatured Ratio Estimation, AISTATS'22. [\\[paper\\]]() [\\[official code\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.11585)\n* EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting, WWW'22. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.08771) \n\n\n\n\n\n## AI4TS Papers 2021 \n\n### NeurIPS 2021\n#### Time Series Forecasting\n* Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.13008) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002Fautoformer)\n* MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.14354) \n* Conformal Time-Series Forecasting [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F312f1ba2a72318edaaa995a67835fad5-Abstract.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fkamilest\u002Fconformal-rnn)\n* Probabilistic Forecasting: A Level-Set Approach [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F32b127307a606effdcc8e51f60a45922-Abstract.html) \n* Topological Attention for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.09031) \n* When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.03904) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FEpiFNP)\n* Monash Time Series Forecasting Archive [\\[paper\\]](https:\u002F\u002Fdatasets-benchmarks-proceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Feddea82ad2755b24c4e168c5fc2ebd40-Abstract-round2.html) [\\[official code\\]](https:\u002F\u002Fforecastingdata.org\u002F)  \n\n#### Time Series Anomaly Detection\n* Revisiting Time Series Outlier Detection: Definitions and Benchmarks [\\[paper\\]](https:\u002F\u002Fdatasets-benchmarks-proceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fec5decca5ed3d6b8079e2e7e7bacc9f2-Abstract-round1.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fdatamllab\u002Ftods\u002Ftree\u002Fbenchmark)   \n* Online false discovery rate control for anomaly detection in time series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.03196)  \n* Detecting Anomalous Event Sequences with Temporal Point Processes [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.04465) \n\n#### Other Time Series Analysis\n* Probabilistic Transformer For Time Series Analysis [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fc68bd9055776bf38d8fc43c0ed283678-Abstract.html) \n* Shifted Chunk Transformer for Spatio-Temporal Representational Learning [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.11575) \n* Deep Explicit Duration Switching Models for Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=LaM6G4yrMy0) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fabdulfatir\u002FREDSDS)\n* Time-series Generation by Contrastive Imitation [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=RHZs3GqLBwg)  \n* CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.03502) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fermongroup\u002Fcsdi)\n* Adjusting for Autocorrelated Errors in Neural Networks for Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.12578) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDaikon-Sun\u002FAdjustAutocorrelation)\n* SSMF: Shifting Seasonal Matrix Factorization [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.12763) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fkokikwbt\u002Fssmf)\n* Coresets for Time Series Clustering [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.15263)  \n* Neural Flows: Efficient Alternative to Neural ODEs [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.13040) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmbilos\u002Fneural-flows-experiments)\n* Spatio-Temporal Variational Gaussian Processes [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2111.01732.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Faaltoml\u002Fspatio-temporal-gps)\n* Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=A_Aeb-XLozL) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FSamsungLabs\u002FDrop-DTW) \n\n\n\n### ICML 2021\n#### Time Series Forecasting\n* Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.12072) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002Fpytorch-ts)\n* End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Frangapuram21a.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Frshyamsundar\u002Fgluonts-hierarchical-ICML-2021)\n* RNN with particle flow for probabilistic spatio-temporal forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06064) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fnetworkslab\u002Frnn_flow)\n* Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.04100) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FZ-GCNETs\u002FZ-GCNETs)\n* Variance Reduction in Training Forecasting Models with Subgroup Sampling [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.02062)  \n* Explaining Time Series Predictions With Dynamic Masks [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.05303) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FJonathanCrabbe\u002FDynamask)\n* Conformal prediction interval for dynamic time-series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.09107) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fhamrel-cxu\u002FEnbPI)\n\n#### Time Series Anomaly Detection\n* Neural Transformation Learning for Deep Anomaly Detection Beyond Images [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.16440) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fboschresearch\u002FNeuTraL-AD)\n* Event Outlier Detection in Continuous Time [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.09522) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsiqil\u002FCPPOD)\n\n#### Other Time Series Analysis\n* Voice2Series: Reprogramming Acoustic Models for Time Series Classification [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.09296) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fhuckiyang\u002FVoice2Series-Reprogramming)\n* Neural Rough Differential Equations for Long Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.08295) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjambo6\u002FneuralRDEs)\n* Neural Spatio-Temporal Point Processes [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.04583) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fneural_stpp)\n* Learning Neural Event Functions for Ordinary Differential Equations [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.03902) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Frtqichen\u002Ftorchdiffeq)\n* Approximation Theory of Convolutional Architectures for Time Series Modelling [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.09355) \n* Whittle Networks: A Deep Likelihood Model for Time Series [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fyu21c.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fml-research\u002FWhittleNetworks)\n* Necessary and sufficient conditions for causal feature selection in time series with latent common causes [\\[paper\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fmastakouri21a.html)  \n\n\n### ICLR 2021\n#### Time Series Forecasting\n* Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WiGQBFuVRv) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002Fpytorch-ts) \n* Discrete Graph Structure Learning for Forecasting Multiple Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WEHSlH5mOk) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fchaoshangcs\u002FGTS)\n\n#### Other Time Series Analysis\n* Clairvoyance: A Pipeline Toolkit for Medical Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xnC8YwKUE3k) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fvanderschaarlab\u002Fclairvoyance)\n* Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=8qDwejCuCN) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsanatonek\u002FTNC_representation_learning)\n* Multi-Time Attention Networks for Irregularly Sampled Time Series [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4c0J6lwQ4_) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Freml-lab\u002FmTAN)\n* Generative Time-series Modeling with Fourier Flows [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=PpshD0AXfA) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fahmedmalaa\u002FFourier-flows)\n* Differentiable Segmentation of Sequences [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4T489T4yav) [\\[slides\\]](https:\u002F\u002Ficlr.cc\u002Fmedia\u002FSlides\u002Ficlr\u002F2021\u002Fvirtual(05-08-00)-05-08-00UTC-2993-differentiable_.pdf)  [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fdiozaka\u002Fdiffseg) \n* Neural ODE Processes [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=27acGyyI1BY) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fcrisbodnar\u002Fndp) \n* Learning Continuous-Time Dynamics by Stochastic Differential Networks [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=U850oxFSKmN) [\\[official code\\]]() \n\n \n### KDD 2021\n#### Time Series Forecasting\n* ST-Norm: Spatial and Temporal Normalization for Multi-variate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467330) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FST-Norm)\n* Graph Deep Factors for Forecasting with Applications to Cloud Resource Allocation [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467357)  \n* Quantifying Uncertainty in Deep Spatiotemporal Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.11982) \n* Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.12931) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsquare-coder\u002FSTGODE)\n* TrajNet: A Trajectory-Based Deep Learning Model for Traffic Prediction [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467236)  \n* Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467275) \n\n\n#### Time Series Anomaly Detection\n* Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding [\\[paper\\]](https:\u002F\u002Fnetman.aiops.org\u002Fwp-content\u002Fuploads\u002F2021\u002F08\u002FKDD21_InterFusion_Li.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fzhhlee\u002FInterFusion)\n* Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467174) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FeBay\u002FRANSynCoders)\n* Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07992) [\\[official code\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07992)\n* Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.13361) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fwzwtrevor\u002FMulti-Scale-One-Class-Recurrent-Neural-Networks)\n\n#### Other Time Series Analysis\n* Representation Learning of Multivariate Time Series using a Transformer Framework [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.02803) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fgzerveas\u002Fmvts_transformer)\n* Causal and Interpretable Rules for Time Series Analysis [\\[paper\\]](https:\u002F\u002Fjosselin-garnier.org\u002Fwp-content\u002Fuploads\u002F2021\u002F10\u002Fkdd21.pdf)  \n* MiniRocket: A Fast (Almost) Deterministic Transform for Time Series Classification [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.08791) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fangus924\u002Fminirocket)\n* Statistical models coupling allows for complex localmultivariate time series analysis [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467362)\n* Fast and Accurate Partial Fourier Transform for Time Series Data [\\[paper\\]](https:\u002F\u002Fjungijang.github.io\u002Fresources\u002F2021\u002FKDD\u002Fpft.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsnudatalab\u002FPFT)\n* Deep Learning Embeddings for Data Series Similarity Search [\\[paper\\]](https:\u002F\u002Fqtwang.github.io\u002Fassets\u002Fpdf\u002Fkdd21-seanet.pdf) [\\[link\\]](https:\u002F\u002Fqtwang.github.io\u002Fkdd21-seanet)\n\n\n### AAAI 2021\n#### Time Series Forecasting \n* Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.07436) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fzhouhaoyi\u002FInformer2020) \n* Deep Switching Auto-Regressive Factorization: Application to Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.05135) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fostadabbas\u002FDSARF)\n* Dynamic Gaussian Mixture Based Deep Generative Model for Robust Forecasting on Sparse Multivariate Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.02164) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2)\n* Temporal Latent Autoencoder: A Method for Probabilistic Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.10460)  \n* Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.00431)  \n* Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.02887) \n* Attentive Neural Point Processes for Event Forecasting [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16929) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fguyulongcs\u002FAAAI2021_ANPP) \n* Forecasting Reservoir Inflow via Recurrent Neural ODEs [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17763)  \n* Hierarchical Graph Convolution Network for Traffic Forecasting [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16088) \n* Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.04038) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjillbetty001\u002FST-GDN) \n* Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.09641) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FMengzhangLI\u002FSTFGNN) \n* FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.15531) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fboreshkinai\u002Ffc-gaga) \n* Fairness in Forecasting and Learning Linear Dynamical Systems [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.07315) \n* A Multi-Step-Ahead Markov Conditional Forward Model with Cube Perturbations for Extreme Weather Forecasting [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16856)  \n* Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16090)  \n\n#### Time Series Anomaly Detection\n* Graph Neural Network-Based Anomaly Detection in Multivariate Time Series [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06947) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fd-ailin\u002FGDN) \n* Time Series Anomaly Detection with Multiresolution Ensemble Decoding [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17152)  \n* Outlier Impact Characterization for Time Series Data [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17379) \n\n#### Time Series Classification\n* Correlative Channel-Aware Fusion for Multi-View Time Series Classification [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16830\u002F16637)\n* Learnable Dynamic Temporal Pooling for Time Series Classification [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.02577) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fdonalee\u002FDTW-Pool)\n* ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series Classification [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17018) \n* Joint-Label Learning by Dual Augmentation for Time Series Classification [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17071)  \n\n#### Other Time Series Analysis\n*  Time Series Domain Adaptation via Sparse Associative Structure Alignment [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.11797) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDMIRLAB-Group\u002FSASA)\n*  Learning Representations for Incomplete Time Series Clustering [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17070)  \n*  Generative Semi-Supervised Learning for Multivariate Time Series Imputation [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17086) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation) \n*  Second Order Techniques for Learning Time-Series with Structural Breaks [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17117)  \n\n\n\n### IJCAI 2021\n#### Time Series Forecasting\n* Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F397)  \n* Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F374)  \n* Hierarchical Adaptive Temporal-Relational Modeling for Stock Trend Prediction [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0508.pdf) \n* TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06273) [\\[official code\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06273) \n\n#### Other Time Series Analysis\n* Time Series Data Augmentation for Deep Learning: A Survey [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12478) \n* Time-Series Representation Learning via Temporal and Contextual Contrasting [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.14112) [\\[official code\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.14112) \n* Adversarial Spectral Kernel Matching for Unsupervised Time Series Domain Adaptation [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F378) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjarheadjoe\u002FAdv-spec-ker-matching) \n* Time-Aware Multi-Scale RNNs for Time Series Modeling [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F315)  \n* TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.00412)   \n\n\n\u003C!--  [\\[paper\\]]() [\\[official code\\]]()  --> \n### SIGMOD VLDB ICDE 2021\n#### Time Series Forecasting\n* AutoAI-TS:AutoAI for Time Series Forecasting, SIGMOD'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.12347)  \n* FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data, VLDB'21. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp721-ding.pdf)\n* MDTP: a multi-source deep traffic prediction framework over spatio-temporal trajectory data, VLDB'21. [\\[paper\\]]()\n* EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting, ICDE'21. [\\[paper\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458855) [\\[slides\\]](https:\u002F\u002Fpdfs.semanticscholar.org\u002F3cb0\u002F6f67fbfcf3c2dac32c02248a03eb84cc246d.pdf)  \n* An Effective Joint Prediction Model for Travel Demands and Traffic Flows, ICDE'21. [\\[paper\\]](https:\u002F\u002Fdbgroup.cs.tsinghua.edu.cn\u002Fligl\u002Fpapers\u002Ficde21-traffic.pdf)  \n \n#### Time Series Anomaly Detection\n* Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series, VLDB'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.05073) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fexathlonbenchmark\u002Fexathlon)\n* SAND: Streaming Subsequence Anomaly Detection, VLDB'21. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp1717-boniol.pdf)  \n\n#### Other Time Series Analysis\n* RobustPeriod: Robust Time-Frequency Mining for Multiple Periodicity Detection, SIGMOD'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.09535) [\\[code\\]](https:\u002F\u002Fgithub.com\u002Fariaghora\u002Frobust-period)\n* ORBITS: Online Recovery of Missing Values in Multiple Time Series Streams, VLDB'21. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp294-khayati.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FeXascaleInfolab\u002Forbits)\n* Missing Value Imputation on Multidimensional Time Series, VLDB'21. [\\[paper\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp2533-bansal.pdf) \n\n\u003C!--    , WSDM'21. [\\[paper\\]]() [\\[official code\\]]()   --> \n### Misc 2021\n#### Time Series Forecasting\n* DeepFEC: Energy Consumption Prediction under Real-World Driving Conditions for Smart Cities, WWW'21. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3442381.3449983) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FElmiSay\u002FDeepFEC)\n* AutoSTG: Neural Architecture Search for Predictions of Spatio-Temporal Graph, WWW'21. [\\[paper\\]](http:\u002F\u002Fpanzheyi.cc\u002Fpublication\u002Fpan2021autostg\u002Fpaper.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fpanzheyi\u002FAutoSTG)\n* REST: Reciprocal Framework for Spatiotemporal-coupled Predictions, WWW'21. [\\[paper\\]](https:\u002F\u002Fs2.smu.edu\u002F~jiazhang\u002FPapers\u002FJiaZhang-WWW2021-REST.pdf)\n* Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series, AISTATS'21. [\\[paper\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv130\u002Fhan21a\u002Fhan21a.pdf)  \n* SSDNet: State Space Decomposition Neural Network for Time Series Forecasting, ICDM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.10251)  \n* AdaRNN: Adaptive Learning and Forecasting of Time Series, CIKM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.04443) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjindongwang\u002Ftransferlearning\u002Ftree\u002Fmaster\u002Fcode\u002Fdeep\u002Fadarnn)\n* Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction, CIKM'21. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3459637.3482271)  \n* Stock Trend Prediction with Multi-Granularity Data: A Contrastive Learning Approach with Adaptive Fusion, CIKM'21. [\\[paper\\]](http:\u002F\u002Fstaff.ustc.edu.cn\u002F~cheneh\u002Fpaper_pdf\u002F2021\u002FMin-Hou-CIKM.pdf)  \n* DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction, CIKM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.09091) [\\[official code1\\]](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002Fdl-traff-graph) [\\[official code2\\]](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002Fdl-traff-grid)\n* Long Horizon Forecasting With Temporal Point Processes, WSDM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.02815) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002FDualTPP)\n* Time-Series Event Prediction with Evolutionary State Graph, WSDM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05006) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FVachelHU\u002FEvoNet).\n\n#### Time Series Anomaly Detection\n* SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs, WWW'21. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3442381.3450013) \n* Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding, WWW'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.14097) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fcruiseresearchgroup\u002FTSCP2)\n* FluxEV: A Fast and Effective Unsupervised Framework for Time-Series Anomaly Detection, WSDM'21. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3437963.3441823) \n* Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping, ICCV'21. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3437963.3441823) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fdonalee\u002Fwetas)\n* Jump-Starting Multivariate Time Series Anomaly Detection for Online Service Systems, ATC'21. [\\[paper\\]](https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fatc21\u002Fpresentation\u002Fma)\n\n\n\n#### Other Time Series Analysis\n* Network of Tensor Time Series, WWW'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07736) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FNET3)\n* Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series, WWW'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07289) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Falasdairtran\u002Fradflow)\n* SrVARM: State Regularized Vector Autoregressive Model for Joint Learning of Hidden State Transitions and State-Dependent Inter-Variable Dependencies from Multi-variate Time Series, WWW'21. [\\[paper\\]](https:\u002F\u002Ffaculty.ist.psu.edu\u002Fvhonavar\u002FPapers\u002FSRVARM.pdf)  \n* Deep Fourier Kernel for Self-Attentive Point Processes, AISTATS'21. [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv130\u002Fzhu21b.html)\n* Differentiable Divergences Between Time Series, AISTATS'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08354) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fsoft-dtw-divergences) \n* Aligning Time Series on Incomparable Spaces, AISTATS'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.12648) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsamcohen16\u002FAligning-Time-Series) \n* Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions, ICDM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.06852)  \n* Towards Generating Real-World Time Series Data, ICDM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.08386) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Facphile\u002FRTSGAN)\n* Learning Saliency Maps to Explain Deep Time Series Classifiers, CIKM'21. [\\[paper\\]](https:\u002F\u002Fkingspp.github.io\u002Fpublications\u002F) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fkingspp\u002Ftimeseries-explain)\n* Actionable Insights in Urban Multivariate Time-series, CIKM'21. [\\[paper\\]](https:\u002F\u002Fpeople.cs.vt.edu\u002Fanikat1\u002Fpublications\u002Fratss-cikm2021.pdf) \n* Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals, WSDM'21. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.11631)  \n\n\n## AI4TS Papers 201X-2020 Selected\n\n### NeurIPS 201X-2020\n\n#### Time Series Forecasting\n* Adversarial Sparse Transformer for Time Series Forecasting, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002F\u002Fpaper\u002F2020\u002Ffile\u002Fc6b8c8d762da15fa8dbbdfb6baf9e260-Paper.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fhihihihiwsf\u002FAST) \n* Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.07719) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FStemGNN) \n* Deep Rao-Blackwellised Particle Filters for Time Series Forecasting, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fafb0b97df87090596ae7c503f60bb23f-Abstract.html) \n* Probabilistic Time Series Forecasting with Shape and Temporal Diversity, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.07349) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fvincent-leguen\u002FSTRIPE) \n* Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.02842) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FLeiBAI\u002FAGCRN) \n* Interpretable Sequence Learning for Covid-19 Forecasting, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.00646) \n* Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.00235) [\\[code\\]](https:\u002F\u002Fgithub.com\u002Fmlpotter\u002FTransformer_Time_Series) \n* Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.03806) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Frajatsen91\u002Fdeepglo) \n* High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.03002) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmbohlkeschneider\u002Fgluon-ts) \n* Deep State Space Models for Time Series Forecasting, NeurIPS'18. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2018\u002Fhash\u002F5cf68969fb67aa6082363a6d4e6468e2-Abstract.html)  \n* Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction, NeurIPS'16. [\\[paper\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2016\u002Fhash\u002F85422afb467e9456013a2a51d4dff702-Abstract.html)  \n\n#### Time Series Anomaly Detection\n* Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F97e401a02082021fd24957f852e0e475-Abstract.html)  \n* PIDForest: Anomaly Detection via Partial Identification, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.03582) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fvatsalsharan\u002Fpidforest) \n* Precision and Recall for Time Series, NeurIPS'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1803.03639) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FIntelLabs\u002FTSAD-Evaluator) \n\n#### Time Series Classification\n* Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F76d7c0780ceb8fbf964c102ebc16d75f-Abstract.html)  \n#### Time Series Clustering\n* Learning Representations for Time Series Clustering, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2019\u002Fhash\u002F1359aa933b48b754a2f54adb688bfa77-Abstract.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fqianlima-lab\u002FDTCR) \n* Learning low-dimensional state embeddings and metastable clusters from time series data, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.00302)\n\n#### Time Series Imputation\n* NAOMI: Non-autoregressive multiresolution sequence imputation, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.10946) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Ffelixykliu\u002FNAOMI) \n* BRITS: Bidirectional Recurrent Imputation for Time Series, NeurIPS'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.10572) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fcaow13\u002FBRITS) \n* Multivariate Time Series Imputation with Generative Adversarial Networks, NeurIPS'18. [\\[paper\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2018\u002Fhash\u002F96b9bff013acedfb1d140579e2fbeb63-Abstract.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FLuoyonghong\u002FMultivariate-Time-Series-Imputation-with-Generative-Adversarial-Networks) \n\n#### Time Series Neural xDE\n* Neural Controlled Differential Equations for Irregular Time Series, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.08926) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fpatrick-kidger\u002FNeuralCDE)  \n* GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.12374) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fedebrouwer\u002Fgru_ode_bayes)  \n* Latent Ordinary Differential Equations for Irregularly-Sampled Time Series, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.03907) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FYuliaRubanova\u002Flatent_ode)  \n* Neural Ordinary Differential Equations, NeurIPS'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.07366) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Frtqichen\u002Ftorchdiffeq)  \n\n#### General Time Series Analysis \n* High-recall causal discovery for autocorrelated time series with latent confounders, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F94e70705efae423efda1088614128d0b-Abstract.html) [\\[paper2\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.01884) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjakobrunge\u002Ftigramite) \n* Benchmarking Deep Learning Interpretability in Time Series Predictions, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.13924) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fayaabdelsalam91\u002FTS-Interpretability-Benchmark)\n* What went wrong and when? Instance-wise feature importance for time-series black-box models, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.02821) [\\[official code\\]]()\n* Normalizing Kalman Filters for Multivariate Time Series Analysis, NeurIPS'20. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F1f47cef5e38c952f94c5d61726027439-Abstract.html)\n* Unsupervised Scalable Representation Learning for Multivariate Time Series, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.10738) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FWhite-Link\u002FUnsupervisedScalableRepresentationLearningTimeSeries)\n* Time-series Generative Adversarial Networks, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fc9efe5f26cd17ba6216bbe2a7d26d490-Abstract.html) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjsyoon0823\u002FTimeGAN) \n* U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging, NeurIPS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.11162) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fperslev\u002FU-Time) \n* Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders, NeurIPS'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.10107)\n* Safe Active Learning for Time-Series Modeling with Gaussian Processes, NeurIPS'18. [\\[paper\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2018\u002Fhash\u002Fb197ffdef2ddc3308584dce7afa3661b-Abstract.html)  \n \n### ICML 201X-2020\n\n#### General Time Series Analysis\n* Learning from Irregularly-Sampled Time Series: A Missing Data Perspective, ICML'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.07599) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsteveli\u002Fpartial-encoder-decoder)\n* Set Functions for Time Series, ICML'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.12064) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FBorgwardtLab\u002FSet_Functions_for_Time_Series)\n* Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders, ICML'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00450) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FTime-Series-Deconfounder)\n* Spectral Subsampling MCMC for Stationary Time Series, ICML'20. [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fsalomone20a.html)  \n* Learnable Group Transform For Time-Series, ICML'20. [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fcosentino20a.html) \n* Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models, ICML'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.10857) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FBiwei-Huang\u002FCausal-discovery-and-forecasting-in-nonstationary-environments)\n* Discovering Latent Covariance Structures for Multiple Time Series, ICML'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.09528) \n* Autoregressive convolutional neural networks for asynchronous time series, ICML'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.04122) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmbinkowski\u002Fnntimeseries)\n* Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series, ICML'18. [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fche18a.html)  \n* Soft-DTW: a Differentiable Loss Function for Time-Series, ICML'17. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.01541) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmblondel\u002Fsoft-dtw)\n\n\n#### Time Series Forecasting\n* Forecasting Sequential Data Using Consistent Koopman Autoencoders, ICML'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.02236) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Ferichson\u002FkoopmanAE)\n* Adversarial Attacks on Probabilistic Autoregressive Forecasting Models, ICML'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.03778) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Feth-sri\u002Fprobabilistic-forecasts-attacks)\n* Influenza Forecasting Framework based on Gaussian Processes, ICML'20. [\\[paper\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fzimmer20a.html) \n* Deep Factors for Forecasting, ICML'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.12417)  \n* Coherent Probabilistic Forecasts for Hierarchical Time Series, ICML'17. [\\[paper\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Ftaieb17a.html) \n\n### ICLR 201X-2020\n#### General Time Series Analysis\n* Interpolation-Prediction Networks for Irregularly Sampled Time Series, ICLR'19. [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1efr3C9Ym) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmlds-lab\u002Finterp-net)\n* SOM-VAE: Interpretable Discrete Representation Learning on Time Series, ICLR'19. [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=rygjcsR9Y7) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fratschlab\u002FSOM-VAE)\n\n#### Time Series Forecasting\n* N-BEATS: Neural basis expansion analysis for interpretable time series forecasting, ICLR'20. [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1ecqn4YwB) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FElementAI\u002FN-BEATS)\n* Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting, ICLR'18. [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=SJiHXGWAZ) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fliyaguang\u002FDCRNN) \n* Automatically Inferring Data Quality for Spatiotemporal Forecasting, ICLR'18. [\\[paper\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ByJIWUnpW) \n\n \n### KDD 201X-2020\n\n#### General Time Series Analysis\n* Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns, KDD'20. [\\[paper\\]](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FQingsong-Wen\u002Fpublication\u002F343780200_Fast_RobustSTL_Efficient_and_Robust_Seasonal-Trend_Decomposition_for_Time_Series_with_Complex_Patterns\u002Flinks\u002F614b9828a3df59440ba498b3\u002FFast-RobustSTL-Efficient-and-Robust-Seasonal-Trend-Decomposition-for-Time-Series-with-Complex-Patterns.pdf) [\\[code\\]](https:\u002F\u002Fgithub.com\u002Fariaghora\u002Ffast-robust-stl)\n* Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data, KDD'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.10996) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Ffloft\u002Fcodats)\n* Online Amnestic DTW to allow Real-Time Golden Batch Monitoring, KDD'19. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330650) \n* Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis, KDD'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.08946)  \n* Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data, KDD'17. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.03161) \n\n\n#### Time Series Forecasting\n* Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks, KDD'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11650) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FMTGNN)\n* Attention based Multi-Modal New Product Sales Time-series Forecasting, KDD'20. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3394486.3403362)\n* Forecasting the Evolution of Hydropower Generation, KDD'20. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3394486.3403337)\n* Modeling Extreme Events in Time Series Prediction, KDD'19. [\\[paper\\]](http:\u002F\u002Fstaff.ustc.edu.cn\u002F~hexn\u002Fpapers\u002Fkdd19-timeseries.pdf)  \n* Multi-Horizon Time Series Forecasting with Temporal Attention Learning, KDD'19. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330662)\n* Regularized Regression for Hierarchical Forecasting Without Unbiasedness Conditions, KDD'19. [\\[paper\\]](https:\u002F\u002Fsouhaib-bentaieb.com\u002Fpapers\u002F2019_kdd_hts_reg.pdf)\n* Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units, KDD'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.09926) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fpratham16\u002FARU)\n* Dynamic Modeling and Forecasting of Time-evolving Data Streams, KDD'19. [\\[paper\\]](https:\u002F\u002Fwww.dm.sanken.osaka-u.ac.jp\u002F~yasuko\u002FPUBLICATIONS\u002Fkdd19-orbitmap.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fyasuko-matsubara\u002Forbitmap)\n* DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events, KDD'19. [\\[paper\\]](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FRenhe-Jiang\u002Fpublication\u002F334714928_DeepUrbanEvent_A_System_for_Predicting_Citywide_Crowd_Dynamics_at_Big_Events\u002Flinks\u002F5d417167299bf1995b597f28\u002FDeepUrbanEvent-A-System-for-Predicting-Citywide-Crowd-Dynamics-at-Big-Events.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FDeepUrbanEvent)\n* Stock Price Prediction via Discovering Multi-Frequency Trading Patterns, KDD'17. [\\[paper\\]](https:\u002F\u002Fwww.eecs.ucf.edu\u002F~gqi\u002Fpublications\u002Fkdd2017_stock.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction)\n\n#### Time Series Anomaly Detection\n* USAD: UnSupervised Anomaly Detection on Multivariate Time Series, KDD'20. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3394486.3403392) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fmanigalati\u002Fusad)\n* RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks, KDD'20 MiLeTS. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.09545)\n* Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network, KDD'19. [\\[paper\\]](https:\u002F\u002Fnetman.aiops.org\u002Fwp-content\u002Fuploads\u002F2019\u002F08\u002FOmniAnomaly_camera-ready.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002FOmniAnomaly)\n* Time-Series Anomaly Detection Service at Microsoft, KDD'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03821) \n* Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding, KDD'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.04431) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fkhundman\u002Ftelemanom)\n* Anomaly Detection in Streams with Extreme Value Theory, KDD'17. [\\[paper\\]](https:\u002F\u002Fhal.archives-ouvertes.fr\u002Fhal-01640325\u002Fdocument)\n\n\n \n### AAAI 201X-2020\n\n#### General Time Series Analysis\n* Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets, AAAI'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.04143) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fpetecheng\u002FTime2Graph) \n* DATA-GRU: Dual-Attention Time-Aware Gated Recurrent Unit for Irregular Multivariate Time Series, AAAI'20. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5440)\n* Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series, AAAI'20. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5496) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDerronXu\u002FDeepTrends) \n* Factorized Inference in Deep Markov Models for Incomplete Multimodal Time Series, AAAI'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.13570) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fztangent\u002Fmultimodal-dmm) \n* Relation Inference among Sensor Time Series in Smart Buildings with Metric Learning, AAAI'20. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5900) \n* TapNet: Multivariate Time Series Classification with Attentional Prototype Network, AAAI'20. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6165) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fxuczhang\u002Ftapnet) \n* RobustSTL: A Robust Seasonal-Trend Decomposition Procedure for Long Time Series, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4480) [\\[code\\]](https:\u002F\u002Fgithub.com\u002FLeeDoYup\u002FRobustSTL)\n* Estimating the Causal Effect from Partially Observed Time Series, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4281)\n* Adversarial Unsupervised Representation Learning for Activity Time-Series, AAAI'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.06847)\n* Fourier Feature Approximations for Periodic Kernels in Time-Series Modelling, AAAI'18. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11696)\n\n#### Time Series Forecasting\n* Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values, AAAI'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.10273)  \n* Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting, AAAI'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12135) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fyokotatsuya\u002FBHT-ARIMA) \n* Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting, AAAI'20. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5438) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FSTSGCN) \n* Self-Attention ConvLSTM for Spatiotemporal Prediction, AAAI'20. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6819) \n* Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting, AAAI'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.12093)  \n* Spatio-Temporal Graph Structure Learning for Traffic Forecasting, AAAI'20. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5470) \n* GMAN: A Graph Multi-Attention Network for Traffic Prediction, AAAI'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.08415) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fzhengchuanpan\u002FGMAN) \n* Cogra: Concept-drift-aware Stochastic Gradient Descent for Time-series Forecasting, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4383)  \n* Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3877) \n* Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002F\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3881) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FguoshnBJTU\u002FASTGCN-r-pytorch)\n* MRes-RGNN: A Novel Deep Learning based Framework for Traffic Prediction, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3821)\n* DeepSTN+: Context-aware Spatial Temporal Neural Network for Crowd Flow Prediction in Metropolis, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3892) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FFIBLAB\u002FDeepSTN)\n* Incomplete Label Multi-task Deep Learning for Spatio-temporal Event Subtype Forecasting, AAAI'19. [\\[paper\\]](http:\u002F\u002Fcs.emory.edu\u002F~lzhao41\u002Fmaterials\u002Fpapers\u002Fmain_AAAI2019.pdf) \n* Learning Heterogeneous Spatial-Temporal Representation for Bike-sharing Demand Prediction, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3890)  \n* Spatiotemporal Multi-Graph Convolution Network for Ride-hailing Demand Forecasting, AAAI'19. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002F\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4247) \n\n#### Time Series Anomaly Detection\n* A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data, AAAI'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.08055)\n* Non-parametric Outliers Detection in Multiple Time Series A Case Study: Power Grid Data Analysis, AAAI'18. [\\[paper\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11632)\n\n \n### IJCAI 201X-2020\n\n#### General Time Series Analysis\n* RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering, IJCAI'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03751) \n* E2GAN: End-to-End Generative Adversarial Network for Multivariate Time Series Imputation, IJCAI'19. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0429.pdf)\n* Causal Inference in Time Series via Supervised Learning, IJCAI'18. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F282)\n\n#### Time Series Forecasting\n* PewLSTM: Periodic LSTM with Weather-Aware Gating Mechanism for Parking Behavior Prediction, IJCAI'20. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F610) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FNingxuanFeng\u002FPewLSTM)\n* LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks, IJCAI'20. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F326)\n* Cross-Interaction Hierarchical Attention Networks for Urban Anomaly Prediction, IJCAI'20. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F601)\n* Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting, IJCAI'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.00397)\n* Explainable Deep Neural Networks for Multivariate Time Series Predictions, IJCAI'19. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F932)\n* Periodic-CRN: A Convolutional Recurrent Model for Crowd Density Prediction with Recurring Periodic Patterns. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F519)\n* Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1709.04875) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FVeritasYin\u002FSTGCN_IJCAI-18)\n* LC-RNN: A Deep Learning Model for Traffic Speed Prediction. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F482)\n* GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction, IJCAI'18. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F476) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fyoshall\u002FGeoMAN)\n* Hierarchical Electricity Time Series Forecasting for Integrating Consumption Patterns Analysis and Aggregation Consistency, IJCAI'18. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F487)\n* NeuCast: Seasonal Neural Forecast of Power Grid Time Series, IJCAI'18. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F460) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fchenpudigege\u002FNeuCast)\n* A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction, IJCAI'17. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.02971) [\\[code\\]](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fa-dual-stage-attention-based-recurrent-neural)\n* Hybrid Neural Networks for Learning the Trend in Time Series, IJCAI'17. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2017\u002F316)\n\n#### Time Series Anomaly Detection\n* BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series, IJCAI'19. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F616) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fhi-bingo\u002FBeatGAN) \n* Outlier Detection for Time Series with Recurrent Autoencoder Ensembles, IJCAI'19. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F378) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Ftungk\u002FOED) \n* Stochastic Online Anomaly Analysis for Streaming Time Series, IJCAI'17. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2017\u002F0445.pdf)\n\n\n#### Time Series Clustering\n* Linear Time Complexity Time Series Clustering with Symbolic Pattern Forest, IJCAI'19. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F406)\n* Similarity Preserving Representation Learning for Time Series Clustering, IJCAI'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1702.03584)\n\n\n#### Time Series Classification\n* A new attention mechanism to classify multivariate time series, IJCAI'20. [\\[paper\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F277)\n\n \n### SIGMOD VLDB ICDE 201X-2020\n#### General Time Series Analysis\n* Debunking Four Long-Standing Misconceptions of Time-Series Distance Measures, SIGMOD'20. [\\[paper\\]](http:\u002F\u002Fpeople.cs.uchicago.edu\u002F~jopa\u002FPapers\u002FPaparrizosSIGMOD2020.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fjohnpaparrizos\u002FTSDistEval) \n* Database Workload Capacity Planning using Time Series Analysis and Machine Learning, SIGMOD'20. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3318464.3386140) \n* Mind the gap: an experimental evaluation of imputation of missing values techniques in time series, VLDB'20. [\\[paper\\]](http:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol13\u002Fp768-khayati.pdf) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FeXascaleInfolab\u002Fbench-vldb20) \n* Active Model Selection for Positive Unlabeled Time Series Classification, ICDE'20. [\\[paper\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9101367) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fsliang11\u002FActive-Model-Selection-for-PUTSC) \n* ExplainIt! -- A declarative root-cause analysis engine for time series data, SIGMOD'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.08132) \n* Cleanits: A Data Cleaning System for Industrial Time Series, VLDB'19. [\\[paper\\]](https:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol12\u002Fp1786-ding.pdf) \n* Matrix Profile X: VALMOD - Scalable Discovery of Variable-Length Motifs in Data Series, SIGMOD'18. [\\[paper\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fpublications\u002Fsigmod18-valmod.pdf) \n* Effective Temporal Dependence Discovery in Time Series Data, VLDB'18. [\\[paper\\]](https:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol11\u002Fp893-cai.pdf) \n\n#### Time Series Anomaly Detection\n* Series2Graph: graph-based subsequence anomaly detection for time series, VLDB'20. [\\[paper\\]](http:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol13\u002Fp1821-boniol.pdf) [\\[official code\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fseries2graph\u002F) \n* Neighbor Profile: Bagging Nearest Neighbors for Unsupervised Time Series Mining, ICDE'20. [\\[paper\\]](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FYuanduo-He\u002Fpublication\u002F340663191_Neighbor_Profile_Bagging_Nearest_Neighbors_for_Unsupervised_Time_Series_Mining\u002Flinks\u002F5e97d607a6fdcca7891c2a0b\u002FNeighbor-Profile-Bagging-Nearest-Neighbors-for-Unsupervised-Time-Series-Mining.pdf)  \n* Automated Anomaly Detection in Large Sequences, ICDE'20. [\\[paper\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fpublications\u002Ficde20-norm.pdf) [\\[official code\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fnorm\u002F) \n* User-driven error detection for time series with events, ICDE'20. [\\[paper\\]](https:\u002F\u002Fwww.eurecom.fr\u002Fen\u002Fpublication\u002F6192\u002Fdownload\u002Fdata-publi-6192.pdf)\n\n\n\u003C!--    , Misc'20. [\\[paper\\]]() [\\[official code\\]]()   WWW, AISTAT, CIKM, ICDM, WSDM, SIGIR, ATC, etc. --> \n### Misc 201X-2020\n#### General Time Series Analysis\n* STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks, WWW'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.07849) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fyscacaca\u002FSTFNets)\n* GP-VAE: Deep probabilistic time series imputation, AISTATS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.04155) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Fratschlab\u002FGP-VAE)\n* DYNOTEARS: Structure Learning from Time-Series Data, AISTATS'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.00498)\n* Personalized Imputation on Wearable-Sensory Time Series via Knowledge Transfer, CIKM'20. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3340531.3411879)\n* Order-Preserving Metric Learning for Mining Multivariate Time Series, ICDM'20. [\\[paper\\]](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10233687)\n* Learning Periods from Incomplete Multivariate Time Series, ICDM'20. [\\[paper\\]](http:\u002F\u002Fwww.cs.albany.edu\u002F~petko\u002Flab\u002Fpapers\u002Fzgzb2020icdm.pdf)\n* Foundations of Sequence-to-Sequence Modeling for Time Series, AISTATS'19. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.03714)\n\n#### Time Series Forecasting\n* Hierarchically Structured Transformer Networks for Fine-Grained Spatial Event Forecasting, WWW'20. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3366423.3380296)\n* HTML: Hierarchical Transformer-based Multi-task Learning for Volatility Prediction, WWW'20. [\\[paper\\]](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340385140_HTML_Hierarchical_Transformer-based_Multi-task_Learning_for_Volatility_Prediction) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction)\n* Traffic Flow Prediction via Spatial Temporal Graph Neural Network, WWW'20. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380186)\n* Towards Fine-grained Flow Forecasting: A Graph Attention Approach for Bike Sharing Systems, WWW'20. [\\[paper\\]](https:\u002F\u002Fuconnuclab.github.io\u002Fpublications\u002F2020\u002FConference\u002Fhe-www-2020-a.pdf) \n* Domain Adaptive Multi-Modality Neural Attention Network for Financial Forecasting, WWW'20. [\\[paper\\]](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10161328)\n* Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting, ICDM'20. [\\[paper\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338303)\n* Probabilistic Forecasting with Spline Quantile Function RNNs, AISTATS'19. [\\[paper\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv89\u002Fgasthaus19a.html)\n* DSANet: Dual self-attention network for multivariate time series forecasting, CIKM'19. [\\[paper\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3358132)\n* RESTFul: Resolution-Aware Forecasting of Behavioral Time Series Data, CIKM'18. [\\[paper\\]](https:\u002F\u002Fwww3.nd.edu\u002F~dial\u002Fpublications\u002Fxian2018restful.pdf)\n* Forecasting Wavelet Transformed Time Series with Attentive Neural Networks, ICDM'18. [\\[paper\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8595010)\n* A Flexible Forecasting Framework for Hierarchical Time Series with Seasonal Patterns: A Case Study of Web Traffic, SIGIR'18. [\\[paper\\]](https:\u002F\u002Fpeople.cs.pitt.edu\u002F~milos\u002Fresearch\u002F2018\u002FSIGIR_18_Liu_Hierarchical_Seasonal_TS.pdf)\n* Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks, SIGIR'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.07015) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002Flaiguokun\u002FLSTNet) \n\n#### Time Series Anomaly Detection\n* Multivariate Time-series Anomaly Detection via Graph Attention Network, ICDM'20. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.02040) [\\[code\\]](https:\u002F\u002Fgithub.com\u002FML4ITS\u002Fmtad-gat-pytorch)\n* MERLIN: Parameter-Free Discovery of Arbitrary Length Anomalies in Massive Time Series Archives, ICDM'20. [\\[paper\\]](https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002FMERLIN_Long_version_for_website.pdf) [\\[official code\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fmerlin-find-anomalies\u002FMERLIN) \n* Cross-dataset Time Series Anomaly Detection for Cloud Systems, ATC'19. [\\[paper\\]](https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fatc19\u002Fpresentation\u002Fzhang-xu) \n* Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications, WWW'18. [\\[paper\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.03903) [\\[official code\\]](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002Fdonut)\n\n \n\n","# 时间序列人工智能（AI4TS）论文、教程与综述\n\n[![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re) \n![欢迎提交PR](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-Welcome-green) \n![星标数](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)\n[![访问量徽章](https:\u002F\u002Fbadges.pufler.dev\u002Fvisits\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)](https:\u002F\u002Fbadges.pufler.dev\u002Fvisits\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers)\n\u003C!-- ![复刻数](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers) -->\n\n一份专业整理的列表，收录了近期**时间序列分析人工智能（AI4TS）**领域的论文（附代码）、教程和综述，涵盖时间序列、时空数据、事件数据、序列数据、时序点过程等主题，内容来自**顶级人工智能会议和期刊**。每当相关顶级会议或期刊公布接收论文时，本列表将**尽快更新**。希望这份列表能为对时间序列分析人工智能感兴趣的科研人员和工程师提供帮助。\n\n顶级会议包括：\n- 机器学习：NeurIPS、ICML、ICLR\n- 数据挖掘：KDD、WWW\n- 人工智能：AAAI、IJCAI\n- 数据管理：SIGMOD、VLDB、ICDE\n- 其他（精选）：AISTAT、CIKM、ICDM、WSDM、SIGIR、ICASSP、CVPR、ICCV等\n\n顶级期刊包括（主要用于综述论文）：\nCACM、PIEEE、TPAMI、TKDE、TNNLS、TITS、TIST、SPM、JMLR、JAIR、CSUR、DMKD、KAIS、IJF、arXiv（精选）等\n\n如果您发现任何遗漏的资源（论文\u002F代码）或错误，请随时提出Issue或发起Pull Request。\n\n如需了解**各领域（深度学习、机器学习、数据挖掘、计算机视觉、自然语言处理、语音等）的最新人工智能进展：教程与综述**，请参阅[此仓库](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Fawesome-AI-tutorials-surveys)。\n\n## 最新更新说明\n- [2024年3月4日] 新增ICLR'24、AAAI'24、WWW'24接收的论文！\n- [2023年7月5日] 新增KDD'23接收的论文！\n- [2023年6月20日] 新增ICML'23接收的论文！\n- [2023年2月7日] 新增ICLR'23和AAAI'23接收的论文！\n- [2022年9月18日] 新增NeurIPS'22接收的论文！\n- [2022年7月14日] 新增KDD'22接收的论文！\n- [2022年6月2日] 新增ICML'22、ICLR'22、AAAI'22、IJCAI'22接收的论文！\n\n## 目录\n- [AI4TS教程与综述](#AI4TS-Tutorials-and-Surveys)\n  * [AI4TS教程](#AI4TS-Tutorials)\n  * [AI4TS综述](#AI4TS-Surveys)\n\n- [AI4TS论文2024](#AI4TS-Papers-2024)\n  * [NeurIPS 2024](#NeurIPS-2024)、[ICML 2024](#ICML-2024)、[ICLR 2024](#ICLR-2024)\n  * [KDD 2024](#KDD-2024)、[WWW 2024](#WWW-2024)、[AAAI 2024](#AAAI-2024)、[IJCAI 2024](#IJCAI-2024)\n  * [SIGMOD VLDB ICDE 2024](#SIGMOD-VLDB-ICDE-2024)\n  * [其他2024](#Misc-2024)\n\n- [AI4TS论文2023](#AI4TS-Papers-2023)\n  * [NeurIPS 2023](#NeurIPS-2023)、[ICML 2023](#ICML-2023)、[ICLR 2023](#ICLR-2023)\n  * [KDD 2023](#KDD-2023)、[AAAI 2023](#AAAI-2023)、[IJCAI 2023](#IJCAI-2023)\n  * [SIGMOD VLDB ICDE 2023](#SIGMOD-VLDB-ICDE-2023)\n  * [其他2023](#Misc-2023)\n\n- [AI4TS论文2022](#AI4TS-Papers-2022)\n  * [NeurIPS 2022](#NeurIPS-2022)、[ICML 2022](#ICML-2022)、[ICLR 2022](#ICLR-2022)\n  * [KDD 2022](#KDD-2022)、[AAAI 2022](#AAAI-2022)、[IJCAI 2022](#IJCAI-2022)\n  * [SIGMOD VLDB ICDE 2022](#SIGMOD-VLDB-ICDE-2022)\n  * [其他2022](#Misc-2022)\n\n- [AI4TS论文2021](#AI4TS-Papers-2021)\n  * [NeurIPS 2021](#NeurIPS-2021)、[ICML 2021](#ICML-2021)、[ICLR 2021](#ICLR-2021)\n  * [KDD 2021](#KDD-2021)、[AAAI 2021](#AAAI-2021)、[IJCAI 2021](#IJCAI-2021)\n  * [SIGMOD VLDB ICDE 2021](#SIGMOD-VLDB-ICDE-2021)\n  * [其他2021](#Misc-2021)\n\n- [AI4TS论文201X–2020精选](#AI4TS-Papers-201X-2020-Selected)\n  * [NeurIPS 201X–2020](#NeurIPS-201X-2020)、[ICML 201X–2020](#ICML-201X-2020)、[ICLR 201X–2020](#ICLR-201X-2020)\n  * [KDD 201X–2020](#KDD-201X-2020)、[AAAI 201X–2020](#AAAI-201X-2020)、[IJCAI 201X–2020](#IJCAI-201X-2020)\n  * [SIGMOD VLDB ICDE 201X–2020](#SIGMOD-VLDB-ICDE-201X-2020)\n  * [其他201X–2020](#Misc-201X-2020)\n\n\n## AI4TS教程与综述\n### AI4TS教程\n* 时间序列中的分布外泛化，发表于*AAAI* 2024。[\\[链接\\]](https:\u002F\u002Food-timeseries.github.io\u002F)\n* 鲁棒时间序列分析及其应用：跨学科方法，发表于*ICDM* 2023。[\\[链接\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Ftimeseries-tutorial-icdm2023)\n* 鲁棒时间序列分析及其应用：工业视角，发表于*KDD* 2022。[\\[链接\\]](https:\u002F\u002Fqingsongedu.github.io\u002Ftimeseries-tutorial-kdd-2022\u002F)\n* 医疗健康领域的时间序列：挑战与解决方案，发表于*AAAI* 2022。[\\[链接\\]](https:\u002F\u002Fwww.vanderschaar-lab.com\u002Ftime-series-in-healthcare\u002F)\n* 时间序列异常检测：工具、技术和技巧，发表于*DASFAA* 2022。[\\[链接\\]](https:\u002F\u002Fwww.dasfaa2022.org\u002F\u002Ftutorials\u002FTime%20Series%20Anomaly%20Result%20Master%20File_Dasfaa_2022.pdf)\n* 大型时间序列预测的现代视角，发表于*IJCAI* 2021。[\\[链接\\]](https:\u002F\u002Flovvge.github.io\u002FForecasting-Tutorial-IJCAI-2021\u002F)\n* 可解释人工智能在社会事件预测中的应用：基础、方法与实践，发表于*AAAI* 2021。[\\[链接\\]](https:\u002F\u002Fyue-ning.github.io\u002Faaai-21-tutorial.html)\n* 物理引导的人工智能在大规模时空数据中的应用，发表于*KDD* 2021。[\\[链接\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fkdd2021tutorial\u002Fhome)\n* 深度学习在异常检测中的应用，发表于*KDD & WSDM* 2020。[\\[链接1\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fkdd2020deepeye\u002Fhome) [\\[链接2\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fwsdm2020dlad) [\\[链接3\\]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Fn0qDbKL3UI)\n* 使用开源工具和Azure机器学习构建预测解决方案，发表于*KDD* 2020。[\\[链接\\]](https:\u002F\u002Fchenhuims.github.io\u002Fforecasting\u002F)\n* 解读与解释深度神经网络：以时间序列数据为例，发表于*KDD* 2020。[\\[链接\\]](https:\u002F\u002Fxai.kaist.ac.kr\u002FTutorial\u002F2020\u002F)\n* 大型时间序列预测：理论与实践，发表于*KDD* 2019。[\\[链接\\]](https:\u002F\u002Flovvge.github.io\u002FForecasting-Tutorial-KDD-2019\u002F)\n* 时空事件预测与前兆识别，发表于*KDD* 2019。[\\[链接\\]](http:\u002F\u002Fmason.gmu.edu\u002F~lzhao9\u002Fprojects\u002Fevent_forecasting_tutorial_KDD)\n* 时序点过程的建模与应用，发表于*KDD* 2019。[\\[链接1\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3332298) [\\[链接2\\]](https:\u002F\u002Fthinklab.sjtu.edu.cn\u002FTPP_Tutor_KDD19.html)\n\n### AI4TS 調查研究\n#### 時間序列通用調查\n* 大型語言模型能為時間序列分析帶來什麼啟示，發表於 *arXiv* 2024。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.02713)\n* 面向時間序列與時空數據的大型模型：綜述與展望，發表於 *arXiv* 2023。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.10196) [\\[網站\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002FAwesome-TimeSeries-SpatioTemporal-LM-LLM)\n* 多變量時間序列插補中的深度學習：綜述，發表於 *arXiv* 2024。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.04059) [\\[網站\\]](https:\u002F\u002Fgithub.com\u002Fwenjiedu\u002Fawesome_imputation)\n* 自監督學習在時間序列分析中的應用：分類、進展與前景，發表於 *arXiv* 2023。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.10125) [\\[網站\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002FAwesome-SSL4TS)\n* 圖神經網絡在時間序列中的應用：預測、分類、插補與異常檢測，發表於 *arXiv* 2023。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03759) [\\[網站\\]](https:\u002F\u002Fgithub.com\u002FKimMeen\u002FAwesome-GNN4TS)\n* 時間序列中的變壓器模型：綜述，發表於 *IJCAI* 2023。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07125) [\\[GitHub 倉庫\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Ftime-series-transformers-review)\n* 深度學習中用於時間序列數據增強的技術：綜述，發表於 *IJCAI* 2021。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12478)\n* 神經時序點過程：回顧，發表於 *IJCAI* 2021。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.03528)\n* 時間序列分析中的因果推斷：問題、方法與評估，發表於 *KAIS* 2022。[\\[論文\\]](https:\u002F\u002Fscholar.google.com\u002Fscholar?cluster=15831734748668637115&hl=en&as_sdt=5,48&sciodt=0,48)\n* 時間序列因果發現方法的調查與評估，發表於 *JAIR* 2022。[\\[論文\\]](https:\u002F\u002Fwww.jair.org\u002Findex.php\u002Fjair\u002Farticle\u002Fview\u002F13428\u002F26775)\n* 深度學習在時空數據挖掘中的應用：綜述，發表於 *TKDE* 2020。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04928)\n* 面向時空數據的生成對抗網絡：綜述，發表於 *TIST* 2022。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.08903)\n* 時空數據挖掘：問題與方法綜述，發表於 *CSUR* 2018。[\\[論文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3161602)\n* 不規則采樣時間序列學習的原則、模型與方法綜述，發表於 *NeurIPS 工作坊* 2020。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.00168)\n* 計數時間序列分析：信號處理視角，發表於 *SPM* 2019。[\\[論文\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8700675)\n* 小波變換在非平穩時間序列分析中的應用：回顧，發表於 *Applied Sciences* 2019。[\\[論文\\]](https:\u002F\u002Fwww.mdpi.com\u002F2076-3417\u002F9\u002F7\u002F1345)\n* 格蘭傑因果關係：回顧與最新進展，發表於 *統計及其應用年度評論* 2014。[\\[論文\\]](https:\u002F\u002Fwww.annualreviews.org\u002Fdoi\u002Fepdf\u002F10.1146\u002Fannurev-statistics-040120-010930)\n* 不規則采樣醫療時間序列數據的深度學習方法綜述，發表於 *arXiv* 2020。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.12493)\n* 不止於視覺：多模態與時序數據自監督表徵學習綜述，發表於 *arXiv* 2022。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.02353)\n* 時間序列預訓練模型綜述，發表於 *arXiv* 2023。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.10716) [\\[鏈接\\]](https:\u002F\u002Fgithub.com\u002Fqianlima-lab\u002Ftime-series-ptms)\n* 自監督學習在時間序列分析中的應用：分類、進展與前景，發表於 *arXiv* 2023。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.10125) [\\[網站\\]](https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002FAwesome-SSL4TS)\n* 圖神經網絡在時間序列中的應用：預測、分類、插補與異常檢測，發表於 *arXiv* 2023。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03759) [\\[網站\\]](https:\u002F\u002Fgithub.com\u002FKimMeen\u002FAwesome-GNN4TS)\n\n\n#### 時間序列預測調查\n* 預測：理論與實踐，發表於 *IJF* 2022。[\\[論文\\]](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0169207021001758)\n* 深度學習在時間序列預測中的應用：綜述，發表於 *英國皇家學會哲學交易 A 卷* 2021。[\\[論文\\]](https:\u002F\u002Froyalsocietypublishing.org\u002Fdoi\u002Ffull\u002F10.1098\u002Frsta.2020.0209)\n* 交通預測中的深度學習：方法、分析與未來方向，發表於 *TITS* 2022。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.08555)\n* 大數據時代的事件預測：系統性綜述，發表於 *CSUR* 2022。[\\[論文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3450287)\n* 預測競賽簡史，發表於 *IJF* 2020。[\\[論文\\]](https:\u002F\u002Fwww.monash.edu\u002Fbusiness\u002Febs\u002Four-research\u002Fpublications\u002Febs\u002Fwp03-2019.pdf)\n* 神經預測：介紹與文獻綜述，發表於 *arXiv* 2020。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.10240)\n* 概率預測，發表於 *統計及其應用年度評論* 2014。[\\[論文\\]](https:\u002F\u002Fwww.annualreviews.org\u002Fdoi\u002Fabs\u002F10.1146\u002Fannurev-statistics-062713-085831)\n\n#### 時間序列異常檢測調查\n* 時間序列數據中的離群點\u002F異常檢測綜述，發表於 *CSUR* 2021。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.04236)\n* 物聯網時間序列數據的異常檢測：綜述，發表於 *IEEE 物聯網期刊* 2019。[\\[論文\\]](https:\u002F\u002Feprints.keele.ac.uk\u002F7576\u002F1\u002F08926446.pdf)\n* AIOps 故障管理方法綜述，發表於 *TIST* 2021。[\\[論文\\]](https:\u002F\u002Fjorge-cardoso.github.io\u002Fpublications\u002FPapers\u002FJA-2021-025-Survey_AIOps_Methods_for_Failure_Management.pdf)\n* 序列式（最快）變化檢測：經典結果與新方向，發表於 *IEEE 信息理論領域選集期刊* 2021。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.04186)\n* 時間數據的離群點檢測：綜述，發表於 TKDE'13。[\\[論文\\]](https:\u002F\u002Fromisatriawahono.net\u002Flecture\u002Frm\u002Fsurvey\u002Fmachine%20learning\u002FGupta%20-%20Outlier%20Detection%20for%20Temporal%20Data%20-%202014.pdf)\n* 離散序列的異常檢測：綜述，發表於 TKDE'12。[\\[論文\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F5645624)\n* 异常检测：综述，发表于 CSUR'09。[\\[论文\\]](https:\u002F\u002Farindam.cs.illinois.edu\u002Fpapers\u002F09\u002Fanomaly.pdf)\n \n#### 時間序列分類調查\n* 深度學習在時間序列分類中的應用：回顧，發表於 *數據挖掘與知識發現* 2019。[\\[論文\\]](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10618-019-00619-1?sap-outbound-id=11FC28E054C1A9EB6F54F987D4B526A6EE3495FD&mkt-key=005056A5C6311EE999A3A1E864CDA986)\n* 時間序列早期分類的方法與應用：綜述，發表於 *IEEE 人工智慧交易* 2020。[\\[論文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.02595)\n\n[\\[論文\\]]()\n## AI4TS 2024 年論文\n### NeurIPS 2024\n\n### ICML 2024\n\n### ICLR 2024\n#### 时间序列预测\n* Time-LLM：通过重编程大型语言模型进行时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Unb5CVPtae) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fkimmeen\u002Ftime-llm\u002F)\n* TEST：文本原型对齐嵌入以激活 LLM 的时间序列能力 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Tuh4nZVb0g) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fscxsunchenxi\u002Ftest)\n* TEMPO：基于提示的生成式预训练 Transformer 用于时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=YH5w12OUuU)\n* DAM：用于预测的基础模型 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4NhMhElWqP)\n* CARD：通道对齐的鲁棒混合 Transformer 用于时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=MJksrOhurE) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fwxie9\u002Fcard)\n* Pathformer：具有自适应路径的多尺度 Transformer 用于时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=lJkOCMP2aW) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fdecisionintelligence\u002Fpathformer)\n* iTransformer：反转 Transformer 对时间序列预测有效 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=JePfAI8fah) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002FiTransformer)\n* GAFormer：通过群体感知嵌入增强时间序列 Transformer [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=c56TWtYp0W)\n* Transformer 调制扩散模型用于概率性多元时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=qae04YACHs)\n* RobustTSF：面向含异常值的鲁棒时间序列预测的理论与设计 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ltZ9ianMth) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fhaochenglouis\u002FRobustTSF)\n* ModernTCN：一种用于通用时间序列分析的现代纯卷积结构 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=vpJMJerXHU)\n* TimeMixer：用于时间序列预测的可分解多尺度混合 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=7oLshfEIC2)\n* FITS：用 1 万参数建模时间序列 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=bWcnvZ3qMb)\n* 多分辨率扩散模型用于时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=mmjnr0G8ZY)\n* MG-TSD：具有引导学习过程的多粒度时间序列扩散模型 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=CZiY6OLktd)\n* 可解释的稀疏系统辨识：超越近期深度学习技术的时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=aFWUY3E7ws)\n* TACTiS-2：更好、更快、更简单的注意力型 Copula 用于多元时间序列 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xtOydkE1Ku)\n* 向透明的时间序列预测迈进 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=TYXtXLYHpR)\n* 带有缺失值的时间序列预测的偏置时序卷积图网络 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=O9nZCwdGcG)\n* 重新思考多元时间序列预测中的通道依赖性：从领先指标中学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=JiTVtCUOpS)\n* VQ-TR：用于时间序列预测的向量量化注意力 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=IxpTsFS7mh)\n* Copula Conformal 预测用于多步时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ojIJZDNIBj)\n* ClimODE：基于物理信息的神经 ODE 进行气候预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xuY33XhEGR)\n* STanHop：用于记忆增强型时间序列预测的稀疏串联 Hopfield 模型 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=6iwg437CZs)\n* T-Rep：使用时间嵌入进行时间序列表示学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=3y2TfP966N)\n* 长期序列预测中的周期性解耦框架 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=dp27P5HBBt)\n* 自监督对比学习预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=nBCuRzjqK7)\n\n#### 其他\n* 通过对比和局部稀疏扰动解释时间序列 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=qDdSRaOiyb) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fzichuan-liu\u002FContraLSP)\n* CausalTime：为因果发现基准测试而真实生成的时间序列 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=iad1yyyGme) [\\[官方代码\\]](https:\u002F\u002Fwww.causaltime.cc\u002F)\n* SocioDojo：利用真实世界文本和时间序列构建终身分析代理 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=s9z0HzWJJp)\n* 面向具有不规则和尺度不变模式的金融时间序列的生成式学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=CdjnzWsQax)\n* 在分析不规则时间序列数据时使用稳定的神经随机微分方程 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4VIgNuQ1pY)\n* 时间序列的软对比学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=pAsQSWlDUf)\n* 基于检索的重建用于时间序列对比学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=3zQo5oUvia)\n* 向增强时间序列对比学习迈进：一种动态坏样本挖掘方法 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=K2c04ulKXn)\n* Diffusion-TS：用于通用时间序列生成的可解释扩散 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4h1apFjO99)\n* 通过基于对比的 l-变分推断解缠时间序列表示 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=iI7hZSczxE)\n* 利用生成模型实现神经时间序列数据的无监督对齐 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=9zhHVyLY4K)\n* 条件信息瓶颈方法用于时间序列插补 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=K1mcPiDdOJ)\n* 通过 Koopman VAEs 对规则和不规则时间序列数据进行生成建模 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=eY7sLb0dVF)\n* 学习独立嵌入时间序列片段 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WS7GuBDFa2)\n* 时间序列对比学习的参数化增强 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=EIPLdFy3vp)\n* 基于多实例学习的固有可解释时间序列分类 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xriGRsoAza)\n\n\n### KDD 2024\n\n### WWW 2024\n\n#### 时间序列预测\n* UniTime：一种基于语言的统一模型，用于跨领域时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.09751)\n* 揭示交通流量预测中的延迟效应：基于时空延迟微分方程的视角 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.01231)\n\n#### 时间序列异常检测\n* LARA：一种轻量级且防过拟合的无监督时间序列异常检测重训练方法 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05668)\n* 重新审视VAE在无监督时间序列异常检测中的应用：从频率角度出发 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.02820)\n* 打破时间序列异常检测中时频粒度不匹配的问题 [\\[论文\\]]()\n\n#### 其他\n* 张量时间序列的动态多网络挖掘 [\\[论文\\]]()\n* E2USD：高效且有效的多变量时间序列无监督状态检测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.14041)\n\n  \n### AAAI 2024\n#### 时间序列预测\n* U-Mixer：一种带有平稳性校正的Unet-Mixer架构，用于时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.02236)\n* HDMixer：一种具有可扩展补丁的层次化依赖结构，用于多变量时间序列预测 [\\[论文\\]]()\n* 利用变分层次Transformer考虑多变量时间序列中的非平稳性进行预测 [\\[论文\\]]()\n* 基于极坐标表示的学习：一种极端自适应的长期时间序列预测模型 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.08763)\n* MSGNet：学习多尺度序列间相关性，用于多变量时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.00423)\n* 用于概率性时间序列预测的潜在扩散Transformer [\\[论文\\]]()\n* 用于交通流量预测的时空关键图神经网络 [\\[论文\\]]()\n\n#### 时间序列分类、聚类、异常检测\n* 面向多变量时间序列分类的图感知对比学习 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.05202)\n* 基于扩散语言形状子的时间序列半监督分类 [\\[论文\\]]()\n* 基于注意力功率迭代的节能流式时间序列分类 [\\[论文\\]]()\n* 跨领域对比学习用于时间序列聚类 [\\[论文\\]]()\n* 当模型遇到新常态时：无监督时间序列异常检测中的测试时自适应 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.11976)\n  \n#### 其他\n* TimesURL：用于通用时间序列表征学习的自监督对比学习 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.15709)\n* GraFITi：利用图结构预测不规则采样时间序列 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.12932)\n* IVP-VAE：使用初值问题求解器建模电子健康记录时间序列 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.06741)\n* SimPSI：一种在时间序列数据增强中保留谱信息的简单策略 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.05790)\n* CGS-Mask：让所有人都能直观地进行时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.09513)\n* CUTS+：从不规则时间序列中进行高维因果发现 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.05890)\n* 用于多变量时间序列数据的全连接时空图 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.05305)\n\n  \n## AI4TS论文2023年\n\n### NeurIPS 2023\n#### 时间序列预测\n* OneNet：通过在线集成增强应对概念漂移的时间序列预测模型 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71725)\n* 一网打尽：基于预训练语言模型的强大通用时间序列分析 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70856)\n* 大型语言模型是零样本时间序列预测器 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70543)\n* BasisFormer：基于注意力机制、可学习且可解释基底的时间序列预测 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69976)\n* ContiFormer：用于不规则时间序列建模的连续时间Transformer [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71304)\n* FourierGNN：从纯图视角重新思考多变量时间序列预测 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71159)\n* 频域MLP在时间序列预测中是更有效的学习者 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70726)\n* 非平稳时间序列预测中的自适应归一化：时间切片视角 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72816)\n* WITRAN：用于长时距时间序列预测的水波信息传输与循环加速网络 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69972)\n* 预测、精炼、合成：用于概率性时间序列预测的自引导扩散模型 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70377)\n* 用于时间序列预测的共形PID控制 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69896)\n* SimMTM：一种用于掩码时间序列建模的简单预训练框架 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70829)\n* Koopa：利用库普曼预测器学习非平稳时间序列动态 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72562)\n\n#### 时间序列异常检测、分类\n* 漂移无关紧要：基于扩散重建的动态分解方法，用于不稳定多变量时间序列异常检测 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71195)\n* 基于点\u002F序列重建的名义性得分条件下的时间序列异常检测 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70582)\n* MEMTO：面向多变量时间序列异常检测的记忆引导Transformer [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71519)\n* 将时间序列视为图像：用于不规则采样时间序列的视觉Transformer [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71219)\n* 尺度教学：针对带噪声标签的时间序列分类的鲁棒多尺度训练 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72608)\n\n#### 其他\n* 基于代理变量的子采样时间序列因果发现 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70936)\n* 半平稳时间序列中的因果发现 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71016)\n* 通过自监督模型行为一致性编码时间序列解释 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F69958)\n* 针对时间序列数据的稀疏深度学习：理论与应用 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72629)\n* CrossGNN：通过交叉交互精炼来应对多变量时间序列中的噪声 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70010)\n* WildfireSpreadTS：用于野火蔓延预测的多模态时间序列数据集 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F73593)\n* 基于现代霍普菲尔德网络的时间序列共形预测 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72007)\n* 基于非线性向量自回归延迟嵌入的时间序列核函数 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71521)\n* 关于约束时间序列生成问题的研究 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F72006)\n* 对比一切：面向医学时间序列的多粒度表征学习 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70272)\n* 在混沌中寻找秩序：一种用于对比学习的时间序列新型数据增强方法 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F71014)\n* FOCAL：在因子化正交潜在空间中进行多模态时间序列传感信号的对比学习 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F70617)\n* BioMassters：用于基于多模态卫星时间序列估算森林生物量的基准数据集 [\\[论文\\]](https:\u002F\u002Fneurips.cc\u002Fvirtual\u002F2023\u002Fposter\u002F73499\n\n### ICML 2023 \n#### 时间序列预测\n* 针对时间序列预测的深度时间索引模型学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=pgcfCCNQXO)\n* 多变量概率预测评估中的可靠性区域 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gTGFxnBymb) \n* 学习集成策略的理论保证及其在时间序列预测中的应用 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=YbYMRZbO1Y) \n* 用于多变量时间序列预测的特征编程 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=LVARH5wXM9) \n* 非自回归条件扩散模型用于时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=wZsnZkviro)\n  \n#### 时间序列异常检测、分类、插补及可解释AI\n* 面向原型的无监督多变量时间序列异常检测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=3vO4lS6PuF) \n* 面向缺失数据的时间序列分类的概率插补 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=7pcZLgulIV) \n* 可证明收敛的薛定谔桥及其在概率性时间序列插补中的应用 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=HRmSGZZ1FY) \n* 带有反事实解释的自我可解释时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=JPMT9kjeJi) \n* 学习扰动以解释时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WpeZu6WzTB)\n  \n#### 其他时间序列分析\n* 使用随机过程扩散将时间数据建模为连续函数 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=OUWckW2g3j) \n* 用于时间序列分析的神经随机微分博弈 [\\[论文\\]]() \n* 用于时间序列结构发现的序贯蒙特卡洛学习 [\\[论文\\]]() \n* 面向时间序列标签稀疏性的上下文一致性正则化 [\\[论文\\]]() \n* 面向时间序列的序贯预测性合意推断 [\\[论文\\]]() \n* 通过强自适应在线学习改进的在线合意预测 [\\[论文\\]]() \n* 面向临床时间序列的序贯多维自监督学习 [\\[论文\\]]() \n* SOM-CPC：利用自组织映射进行无监督对比学习，用于高采样率时间序列的结构化表示 [\\[论文\\]]() \n* 面向特征和标签漂移的时间序列领域自适应 [\\[论文\\]]() \n* 用于时间序列生成的深度潜在状态空间模型 [\\[论文\\]]() \n* 用于不规则采样时间序列的神经连续-离散状态空间模型 [\\[论文\\]]() \n* 面向分布外运动预测的生成式因果表征学习 [\\[论文\\]]() \n* 用于学习混沌动力学的广义教师强制 [\\[论文\\]]() \n* 学习稀疏观测相互作用系统的动力学 [\\[论文\\]]() \n* 马尔可夫高斯过程变分自编码器 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Z8QlQ207V6) \n* ClimaX：气象与气候的基础模型 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=TowCaiz7Ui)\n\n\n### ICLR 2023\n#### 时间序列预测\n* 一条时间序列胜过64个词：基于Transformer的长期预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Jbdc0vTOcol) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fyuqinie98\u002FPatchTST)\n* Crossformer：利用跨维度依赖进行多变量时间序列预测的Transformer [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=vSVLM2j9eie) [\\[官方代码\\]]()\n* Scaleformer：用于时间序列预测的迭代多尺度精炼Transformer [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=sCrnllCtjoE) [\\[官方代码\\]]()\n* MICN：用于长期序列预测的多尺度局部与全局上下文建模 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=zt53IDUR1U) [\\[官方代码\\]]()\n* 用于少样本高维时间序列预测的序贯潜在变量模型 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=7C9aRX2nBf2) [\\[官方代码\\]]()\n* 为时间序列预测而学习快与慢 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=q-PbpHD3EOk) [\\[官方代码\\]]()\n* 面向具有时间分布变化的时间序列的库普曼神经算子预测器 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=kUmdmHxK5N) [\\[官方代码\\]]()\n* 鲁棒的多变量时间序列预测：对抗攻击与防御机制 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ctmLBs8lITa) [\\[官方代码\\]]()\n\n#### 时间序列异常检测与分类\n* 用于时间序列异常检测的无监督模型选择 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gOZ_pKANaPW) [\\[官方代码\\]]()\n* 面向时间序列分类的分布外表征学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gUZWOE42l6Q) [\\[官方代码\\]]()\n\n#### 其他时间序列分析\n* 用简单的离散状态空间有效建模时间序列 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=2EpjkjzdCAa) [\\[官方代码\\]]()\n* TimesNet：面向通用时间序列分析的时序二维变异建模 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ju_Uqw384Oq) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002FTime-Series-Library)\n* 面向时间序列无监督领域自适应的对比学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xPkJYRsQGM) [\\[官方代码\\]]()\n* 递归式时间序列数据增强 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=5lgD4vU-l24s) [\\[官方代码\\]]()\n* 基于解耦时空表征的多变量时间序列插补 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=rdjeCNUS6TG) [\\[官方代码\\]]()\n* 用于端到端学习对齐路径的深度声明式动态时间规整 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=UClBPxIZqnY) [\\[官方代码\\]]()\n* Rhino：带有历史相关噪声的深度因果时序关系学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=i_1rbq8yFWC) [\\[官方代码\\]]()\n* CUTS：从非结构化时间序列数据中进行神经因果发现 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=UG8bQcD3Emv) [\\[官方代码\\]]()\n* 时间序列预测中特征重要性的时序依赖 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=C0q9oBc3n4) [\\[官方代码\\]]()\n\n### KDD 2023\n#### 时间序列异常检测\n* DCdetector：用于时间序列异常检测的双注意力对比表示学习 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.10347) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FKDD2023-DCdetector)\n* 基于插补的时间序列异常检测：条件权重增量扩散模型 [\\[论文\\]](https:\u002F\u002Fgithub.com\u002FChunjingXiao\u002FDiffAD\u002Fblob\u002Fmain\u002FKDD_23_DiffAD.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FChunjingXiao\u002FDiffAD)\n* 非规则时间序列的异常前兆检测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.15489)  \n#### 时间序列预测\n* 当刚性带来负面影响：概率层次化时间序列预测中的软一致性正则化\n* TSMixer：用于多变量时间序列预测的轻量级MLP-Mixer模型 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.09364)\n* 层次代理建模在时间序列预测中改进超参数优化的应用\n* 用于多变量时间序列建模的稀疏二值Transformer [\\[论文\\]]() [\\[官方代码\\]]()\n* 交互式广义加性模型及其在电力负荷预测中的应用\n#### 时间序列预测（交通）\n* Frigate：道路网络上的节俭时空预测 [\\[论文\\]]() [\\[官方代码\\]]()\n* 可迁移的图结构学习：跨城市基于图的交通预测\n* 基于强化动态对抗训练的鲁棒时空交通预测\n* 针对持续交通预测的演化图模式扩展与整合\n#### 时间序列插补\n* 基于时间插补的无源域适应：应用于时间序列数据 [\\[论文\\]]() [\\[官方代码\\]]()\n* 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\n* 观测值一致的扩散模型：用于插补多变量时间序列中的缺失值\n#### 其他\n* 用于余震检测的在线少样本时间序列分类 [\\[论文\\]]() [\\[官方代码\\]]()\n* 利用时间序列动力学进行临床多变量时间序列的自监督分类\n* Warpformer：一种用于不规则临床时间序列的多尺度建模方法\n* 无参数Spikelet：利用自适应时间序列表示发现不同长度和变形的时间序列模式\n* FLAMES2Graph：一个可解释的联邦多变量时间序列分类框架\n* WHEN：一种小波-DTW混合注意力网络，用于异构时间序列分析\n\n### AAAI 2023\n#### 时间序列预测\n* AirFormer：使用Transformer预测中国全国空气质量 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.15979) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fyoshall\u002FAirFormer)\n* Dish-TS：缓解时间序列预测中分布偏移的一般范式 [\\[论文\\]]() [\\[官方代码\\]]()\n* WaveForM：用于多变量时间序列长序列预测的图增强小波学习 [\\[论文\\]]() [\\[官方代码\\]]() \n* Transformer是否适用于时间序列预测 [\\[论文\\]]() [\\[官方代码\\]]()\n* 使用稀疏但信息丰富的变量进行预测：以血糖预测为例 [\\[论文\\]]() [\\[官方代码\\]]()\n* 基于概率增强LSTM神经网络的极端自适应时间序列预测模型 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.15891) [\\[官方代码\\]]()\n* 用于交通预测的时空元图学习 [\\[论文\\]]() [\\[官方代码\\]]()\n\n#### 其他时间序列分析\n* 时间—频率协同训练：用于时间序列半监督学习 [\\[论文\\]]() [\\[官方代码\\]]()\n* 多变量时间序列无监督域适应中的传感器对齐 [\\[论文\\]]() [\\[官方代码\\]]()\n* 用于医学时间序列生成的因果循环变分自编码器 [\\[论文\\]]() [\\[官方代码\\]]()\n* AEC-GAN：用于自回归长时序生成的对抗误差校正GAN [\\[论文\\]]() [\\[官方代码\\]]()\n* SVP-T：一种基于形状层面变量位置变换的多变量时间序列分类变压器 [\\[论文\\]]() [\\[官方代码\\]]()\n\n\n## AI4TS论文集2022\n### NeurIPS 2022\n#### 时间序列预测\n* FiLM：频率改进的勒让德记忆模型，用于长期时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.08897) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FNeurIPS2022-FiLM)\n* SCINet：基于样本卷积与交互作用的时间序列建模与预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.09305) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fcure-lab\u002FSCINet)\n\n* 非平稳Transformer：重新思考时间序列预测中的平稳性 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.14415)\n* Earthformer：探索用于地球系统预测的空间—时间Transformer [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.05833)\n* 基于扩散、去噪与解耦合的生成式时间序列预测\n* 学习潜藏的季节性—趋势表征以用于时间序列预测\n* WaveBound：动态误差约束以实现稳定的时间序列预测\n \n* 时间维度与单纯复形共舞：基于Zigzag滤波曲线的超霍奇卷积网络用于时间序列预测\n \n* 基于时间多项式图神经网络的多变量时间序列预测\n \n* C2FAR：从粗到细的自回归网络，用于精确的概率预测\n \n* 使用任务推理进行元学习的动力学预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.10271)\n \n* 带有时间分位数调整的共形预测\n\n\n\n#### 其他时间序列分析\n* 基于时间—频率一致性的自监督对比预训练，用于时间序列 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.08496) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FTFC-pretraining)\n* 时间序列的因果解耦\n* BILCO：一种高效的时间序列联合对齐算法\n* 用于时间序列分类的动态稀疏网络：学习“看”什么\n* AutoST：迈向时空序列的通用建模\n \n* GT-GAN：基于生成对抗网络的通用时间序列合成\n \n* 利用时间序列特权信息高效学习非线性预测模型\n \n* 对时空交通预测模型的实际对抗攻击\n\n### ICML 2022\n#### 时间序列预测\n* FEDformer：用于长期序列预测的频率增强分解Transformer [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.12740) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FICML2022-FEDformer)\n* TACTiS：面向时间序列的Transformer注意力耦合模型 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.03528) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FServiceNow\u002Ftactis)\n* 基于波动率的核函数与移动平均均值，用于高斯过程的精确预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.06544) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fg-benton\u002Fvolt)\n* 基于注意力共享的时间序列预测领域自适应 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.06828)\n* DSTAGNN：用于交通流量预测的动态时空感知图神经网络 [\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Flan22a.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FSYLan2019\u002FDSTAGNN)\n\n#### 时间序列异常检测\n* 用于多变量时间序列异常检测的深度变分图卷积循环网络 [\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fchen22x.html)\n\n#### 其他时间序列分析\n* 面向时间序列的自适应共形预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07282) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmzaffran\u002Fadaptiveconformalpredictionstimeseries)\n* 使用连续递归单元建模不规则时间序列 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.11344) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fboschresearch\u002Fcontinuous-recurrent-units)\n* 基于迭代双线性时频融合的无监督时间序列表示学习 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.04770)\n* 从多模态时间序列中重建非线性动力系统 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.02922) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fdurstewitzlab\u002Fmmplrnn)\n* 利用专家特征进行时间序列表示的对比学习 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.11517) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fboschresearch\u002Fexpclr)\n* 面向电子健康记录时间序列的基于聚类的特征重要性学习 [\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Faguiar22a.html)\n\n### ICLR 2022\n#### 时间序列预测\n* Pyraformer：用于长距离时间序列建模与预测的低复杂度金字塔型注意力机制 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=0EXmFzUn5I) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Falipay\u002FPyraformer)\n* DEPTS：用于周期性时间序列预测的深度扩展学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=AJAR-JgNw__) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fweifantt\u002Fdepts)\n* CoST：用于时间序列预测的解耦季节-趋势表示的对比学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=PilZY3omXV2) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002FCoST)\n* 可逆实例归一化，用于应对分布偏移的精确时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=cGDAkQo1C0p) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fts-kim\u002FRevIN)\n* TAMP-S2GCNets：将时间感知的多尺度知识表示与空间超图卷积网络相结合，用于时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=wv6g8fWLX2q) [\\[官方代码\\]](https:\u002F\u002Fwww.dropbox.com\u002Fsh\u002Fn0ajd5l0tdeyb80\u002FAABGn-ejfV1YtRwjf_L0AOsNa?dl=0)\n* Back2Future：利用回填动态改进未来实时预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=L01Nn_VJ9i) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FBack2Future)\n* 关于最大似然估计在回归与预测中的优势 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=zrW-LVXj2k1)\n* 学会记忆模式：用于交通预测的模式匹配记忆网络 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=wwDg3bbYBIq) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fhyunwookl\u002Fpm-memnet)\n\n\n#### 时间序列异常检测\n* 异常Transformer：基于关联差异的时间序列异常检测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=LzQQ89U1qm_) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002FAnomaly-Transformer)\n* 图增强归一化流用于多时间序列的异常检测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=45L_dgP48Vd) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fenyandai\u002Fganf)\n\n#### 时间序列分类\n* T-WaveNet：一种用于时间序列信号分析的树状小波神经网络 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=U4uFaLyg7PV)\n* 全尺度CNN：一种简单有效的用于时间序列分类的卷积核尺寸配置方案 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=PDYs7Z2XFGv)\n\n#### 其他时间序列分析\n* 面向不规则采样多变量时间序列的图引导网络 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Kwm8I7dU-l5)\n* 用于不规则采样时间序列的异方差时间变分自编码器 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Az7opqbQE-3)\n* 不规则间隔事件及其参与者的Transformer嵌入 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Rty5g9imm7H)\n* 填补空缺：基于图神经网络的多变量时间序列插补 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=kOu3-S3wJ7)\n* PSA-GAN：用于生成合成时间序列的渐进式自注意力GAN [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=Ix_mh42xq5w)\n* 用于非平稳时间序列分析的Huber加法模型 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=9kpuB2bgnim)\n* LORD：对数签名在神经粗糙微分方程中的低维嵌入 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=fCG75wd39ze)\n* 深度神经网络的嵌入 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=yKIAXjkJc2F)\n* 基于一致性的时间序列标签传播，加速主动学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=gjNcH0hj0LM)\n* 用于序列建模的长表达式记忆 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=vwj6aUeocyf)\n* 自回归分位数流用于预测不确定性估计 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=z1-I6rOKv1S)\n* 基于有限元网络，从稀疏观测中学习物理系统的动力学行为 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=HFmAukZ-k-2)\n* 用于有监督表示学习和少样本序列分类的时间对齐预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=p3DKPQ7uaAi)\n* 通过学习可解释的时间逻辑规则来解释点过程 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=P07dq7iSAGr)\n\n### KDD 2022\n \n#### 时间序列预测\n* 学习旋转：用于复杂周期性时间序列预测的四元数Transformer [\\[代码\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FKDD2022-Quatformer)\n* 学习多变量时间序列预测中的演化与多尺度图结构\n* 预训练增强的多变量时间序列预测时空图神经网络\n* 变量子集上的多变量时间序列预测\n* Greykite：在LinkedIn大规模部署灵活的预测系统\n\n#### 时间序列异常检测\n* 时间序列异常检测算法的局部评估\n* 将时间序列异常检测扩展至数万亿数据点及超高速到达的数据流\n\n#### 其他时间序列\u002F时空分析\n* 面向任务的时间序列Transformer重建\n* 朝着学习时间序列解耦表示的方向\n* ProActive：用于活动序列的自注意力时序点过程流\n* 非平稳、时间感知的核化注意力机制用于时序事件预测\n* MSDR：用于时空预测的多步依赖关系网络\n* Graph2Route：一种用于接送路线预测的动态时空图神经网络\n* 不止于点预测：利用深度极值混合模型捕捉零膨胀与重尾的时空数据\n* 基于时空混杂因子学习的鲁棒事件预测\n* 通过自定步长图对比学习挖掘时空关系\n* 基于跨城市知识迁移的时空图少样本学习\n* 通过时空分解刻画新冠疫情波次\n\n\n### AAAI 2022\n#### 时间序列预测\n* CATN：用于多变量时间序列预测的交叉注意力树感知网络 [\\[论文\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai7403) \n* 基于强化学习的时间序列预测动态模型组合 [\\[论文\\]](https:\u002F\u002Faaai-2022.virtualchair.net\u002Fposter_aaai8424)\n* DDG-DA：用于可预测概念漂移适应的数据分布生成 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.04038) [官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqlib\u002Ftree\u002Fmain\u002Fexamples\u002Fbenchmarks_dynamic\u002FDDG-DA)\n* PrEF：基于Copula增强的状态空间模型的概率电力预测 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aisi7128)\n* LIMREF：针对预测的局部可解释、模型无关规则解释，并应用于电力智能电表数据 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aisi8802)  \n* 亚季节气候预测的学习与动力学模型：比较与合作 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.05196) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FSijie-umn\u002FSSF-MIP)\n* CausalGNN：基于因果推理的时空流行病预测图神经网络 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aisi6475)\n* 用于时空气象预报的条件局部卷积 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.01000) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fbird-tao\u002Fclcrn)\n* 用于交通预测的图神经控制微分方程 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai6502) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FSTG-NCDE)\n* STDEN：迈向物理引导的神经网络用于交通流量预测 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai211) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FEcho-Ji\u002FSTDEN)\n\n#### 时间序列异常检测\n* 朝着严格的时间序列异常检测评估方向 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai2239)  \n* AnomalyKiTS——时间序列异常检测工具包 [\\[演示论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_dm318) \n\n#### 其他时间序列分析\n* TS2Vec：迈向时间序列的通用表示 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai8809) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fyuezhihan\u002Fts2vec)\n* I-SEA：基于重要性采样和期望对齐的深度距离度量学习，用于时间序列分析与嵌入 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai10930)  \n* 训练鲁棒的时间序列领域深度模型：新算法与理论分析 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai4151)  \n* 条件损失与深度欧拉方案用于时间序列生成 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai12878)  \n* 对区间删失时间序列进行聚类以进行疾病表型分类 [\\[论文\\]](https:\u002F\u002Faaai-2022虚拟椅网\u002Fposter_aaai12517)  \n\n\n### IJCAI 2022\n#### 时间序列预测\n* Triformer：三角形、变量特异性注意力机制，用于长序列多变量时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.13767)\n* 长期预测中的一致性概率聚合查询 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.03394) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002Faggforecaster)\n* 结合语义知识的正则化图结构学习，用于多变量时间序列预测\n* DeepExtrema：一种用于预测时间序列数据块极大值的深度学习方法 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.02441) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fgalib19\u002Fdeepextrema-ijcai22-)\n* 用于时间序列预测的记忆增强状态空间模型\n* 基于多分辨率时空数据的物理信息驱动的长序列预测\n* 基于动态多图注意力的长期时空预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.11008) [\\[官方代码\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.11008)\n* FOGS：基于学习图的第一阶梯度监督，用于交通流量预测\n\n#### 时间序列异常检测\n* 神经上下文感知的时间序列异常检测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.07702)  \n* GRELEN：从图关系学习视角出发的多变量时间序列异常检测  \n\n#### 时间序列分类\n* 基于强化学习的信息模式挖掘框架，用于多变量时间序列分类 [\\[论文\\]](https:\u002F\u002Fcpsl.pratt.duke.edu\u002Fsites\u002Fcpsl.pratt.duke.edu\u002Ffiles\u002Fdocs\u002Fgao_ijcai22.pdf)\n* T-SMOTE：面向时间的合成少数类过采样技术，用于不平衡时间序列分类\n\n### SIGMOD VLDB ICDE 2022\n#### 时间序列预测\n* METRO：用于多变量时间序列预测的通用图神经网络框架，VLDB'22。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp224-cui.pdf) [\\[官方代码\\]](https:\u002F\u002Fzheng-kai.com\u002Fcode\u002Fmetro_single_s.zip) \n* AutoCTS：自动相关时间序列预测，VLDB'22。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp971-wu.pdf)\n* 面向时空感知的交通时间序列预测，ICDE'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.15737) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Frazvanc92\u002Fst-wa) \n\n\n#### 时间序列异常检测\n* Sintel：从信号中提取洞察的机器学习框架，SIGMOD'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.09108) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsarahmish\u002Fsintel-paper) \n* TSB-UAD：单变量时间序列异常检测的端到端基准测试套件，VLDB'22。[\\[论文\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fpublications\u002Fpvldb22-tsbuad.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjohnpaparrizos\u002FTSB-UAD)\n* TranAD：用于多变量时间序列数据异常检测的深度变换网络，VLDB'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.07284) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fimperial-qore\u002Ftranad)\n* 基于多样性驱动卷积集成的无监督时间序列离群点检测，VLDB'22。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp611-chaves.pdf)\n* 用于时间序列离群点检测的鲁棒且可解释的自编码器，ICDE'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.03341)\n* 基于鲁棒变分拟循环自编码器的时间序列异常检测，ICDE'22。  \n\n#### 时间序列分类\n* IPS：用于时间序列分类的形状子串实例特征发现，ICDE'22。[\\[论文\\]](https:\u002F\u002Fpersonal.ntu.edu.sg\u002Fassourav\u002Fpapers\u002FICDE-22-IPS.pdf)\n* 面向基于深度学习的时间序列分类的后门攻击，ICDE'22。[\\[论文\\]]()\n\n#### 其他时间序列分析\n* OnlineSTL：将时间序列分解速度提升100倍，VLDB'22。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol15\u002Fp1417-mishra.pdf) \n* 利用互信息高效挖掘大型时间序列中的时序模式，VLDB'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.03653)\n* 学习可演化的时间序列形状子串，ICDE'22。  \n\n\n\u003C!--  [\\[论文\\]]() [\\[官方代码\\]]()  -->  \n### 其他2022年\n#### 时间序列预测\n* CAMul：校准且准确的多视角时间序列预测，WWW'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.07438) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fadityalab\u002Fcamul)\n* 带置信度估计的多粒度残差学习用于时间序列预测，WWW'22。[\\[论文\\]](https:\u002F\u002Fweb.archive.org\u002Fweb\u002F20220426115606id_\u002Fhttps:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3485447.3512056)  \n* RETE：基于统一查询产品进化图的检索增强型时间事件预测，WWW'22。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3485447.3511974) \n* 鲁棒的概率性时间序列预测，AISTATS'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.11910) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Ftetrzim\u002Frobust-probabilistic-forecasting) \n* 用于无分布假设时间序列预测的学习不交叉分位数函数，AISTATS'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.06581)\n\n\n#### 时间序列异常检测\n* TFAD：结合时频分析的分解式时间序列异常检测架构，CIKM'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.09693) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FDAMO-DI-ML\u002FCIKM22-TFAD)\n* 基于层次化潜在因子的深度生成模型用于时间序列异常检测，AISTATS'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.07586) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fcchallu\u002Fdghl)\n* 用于在线系统的多变量时间序列半监督VAE主动异常检测框架，WWW'22。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3485447.3511984) \n\n\n#### 其他时间序列分析\n* 解耦时间序列的局部与全局表征，AISTATS'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.02262) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fgoogleinterns\u002Flocal_global_ts_representation)\n* LIMESegment：有意义、真实的时间序列解释，AISTATS'22。[\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv151\u002Fsivill22a.html)\n* 利用时间序列特权信息进行可证明高效的预测模型学习，AISTATS'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.14993) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FRickardKarl\u002FLearningUsingPrivilegedTimeSeries)\n* 带签名比率估计的昂贵时间序列模拟器的摊销似然自由推断，AISTATS'22。[\\[论文\\]]() [\\[官方代码\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.11585)\n* EXIT：基于外推与插值的神经控制微分方程用于时间序列分类和预测，WWW'22。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.08771) \n\n\n\n\n\n## AI4TS论文2021年\n\n### NeurIPS 2021\n#### 时间序列预测\n* Autoformer：具有自相关性的分解Transformer用于长期序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.13008) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fthuml\u002Fautoformer)\n* MixSeq：将宏观时间序列预测与微观时间序列数据相结合 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.14354) \n* 同余时间序列预测 [\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F312f1ba2a72318edaaa995a67835fad5-Abstract.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fkamilest\u002Fconformal-rnn)\n* 概率预测：基于水平集的方法 [\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002F32b127307a606effdcc8e51f60a45922-Abstract.html) \n* 针对时间序列预测的拓扑注意力 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.09031) \n* 当存疑时：用于流行病预测的神经非参数不确定性量化 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.03904) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FAdityaLab\u002FEpiFNP)\n* 莫纳什时间序列预测档案 [\\[论文\\]](https:\u002F\u002Fdatasets-benchmarks-proceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Feddea82ad2755b24c4e168c5fc2ebd40-Abstract-round2.html) [\\[官方代码\\]](https:\u002F\u002Fforecastingdata.org\u002F)  \n\n#### 时间序列异常检测\n* 重温时间序列离群点检测：定义与基准 [\\[论文\\]](https:\u002F\u002Fdatasets-benchmarks-proceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fec5decca5ed3d6b8079e2e7e7bacc9f2-Abstract-round1.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fdatamllab\u002Ftods\u002Ftree\u002Fbenchmark)   \n* 时间序列异常检测中的在线假发现率控制 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.03196)  \n* 使用时序点过程检测异常事件序列 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.04465) \n\n#### 其他时间序列分析\n* 用于时间序列分析的概率Transformer [\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Fhash\u002Fc68bd9055776bf38d8fc43c0ed283678-Abstract.html) \n* 用于时空表征学习的移位分块Transformer [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.11575) \n* 用于时间序列的深度显式持续时间切换模型 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=LaM6G4yrMy0) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fabdulfatir\u002FREDSDS)\n* 基于对比模仿的时间序列生成 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=RHZs3GqLBwg)  \n* CSDI：用于概率性时间序列插补的条件分数驱动扩散模型 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.03502) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fermongroup\u002Fcsdi)\n* 在时间序列神经网络中调整自相关误差 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.12578) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FDaikon-Sun\u002FAdjustAutocorrelation)\n* SSMF：移动季节性矩阵分解 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.12763) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fkokikwbt\u002Fssmf)\n* 用于时间序列聚类的核集 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.15263)  \n* 神经流：神经ODE的有效替代方案 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.13040) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmbilos\u002Fneural-flows-experiments)\n* 时空变分高斯过程 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2111.01732.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Faaltoml\u002Fspatio-temporal-gps)\n* Drop-DTW：在剔除异常值的同时对齐序列间的共同信号 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=A_Aeb-XLozL) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FSamsungLabs\u002FDrop-DTW) \n\n\n\n### ICML 2021\n#### 时间序列预测\n* 用于多变量概率时间序列预测的自回归去噪扩散模型 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.12072) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002Fpytorch-ts)\n* 分层时间序列一致性概率预测的端到端学习 [\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Frangapuram21a.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Frshyamsundar\u002Fgluonts-hierarchical-ICML-2021)\n* 带有粒子流的RNN用于概率性时空预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06064) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fnetworkslab\u002Frnn_flow)\n* Z-GCNETs：图卷积网络中的时间之字形结构用于时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.04100) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FZ-GCNETs\u002FZ-GCNETs)\n* 通过子组采样降低预测模型训练中的方差 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.02062)  \n* 使用动态掩码解释时间序列预测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.05303) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FJonathanCrabbe\u002FDynamask)\n* 动态时间序列的同余预测区间 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.09107) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fhamrel-cxu\u002FEnbPI)\n\n#### 时间序列异常检测\n* 用于超越图像的深度异常检测的神经变换学习 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.16440) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fboschresearch\u002FNeuTraL-AD)\n* 连续时间中的事件离群点检测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.09522) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsiqil\u002FCPPOD)\n\n#### 其他时间序列分析\n* Voice2Series：为时间序列分类重新编程声学模型 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.09296) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fhuckiyang\u002FVoice2Series-Reprogramming)\n* 用于长时序的神经粗糙微分方程 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.08295) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjambo6\u002FneuralRDEs)\n* 神经时空点过程 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.04583) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fneural_stpp)\n* 学习常微分方程的神经事件函数 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.03902) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Frtqichen\u002Ftorchdiffeq)\n* 用于时间序列建模的卷积架构近似理论 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.09355) \n* Whittle网络：一种用于时间序列的深度似然模型 [\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fyu21c.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fml-research\u002FWhittleNetworks)\n* 具有潜在共同原因的时间序列中因果特征选择的必要和充分条件 [\\[论文\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv139\u002Fmastakouri21a.html)\n\n### ICLR 2021\n#### 时间序列预测\n* 基于条件归一化流的多变量概率时间序列预测 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WiGQBFuVRv) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fzalandoresearch\u002Fpytorch-ts) \n* 用于多时间序列预测的离散图结构学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=WEHSlH5mOk) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fchaoshangcs\u002FGTS)\n\n#### 其他时间序列分析\n* Clairvoyance：面向医疗时间序列的流水线工具包 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=xnC8YwKUE3k) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fvanderschaarlab\u002Fclairvoyance)\n* 基于时间邻域编码的时间序列无监督表征学习 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=8qDwejCuCN) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsanatonek\u002FTNC_representation_learning)\n* 面向不规则采样时间序列的多时间注意力网络 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4c0J6lwQ4_) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Freml-lab\u002FmTAN)\n* 基于傅里叶流的生成式时间序列建模 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=PpshD0AXfA) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fahmedmalaa\u002FFourier-flows)\n* 可微分的序列分割 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=4T489T4yav) [\\[幻灯片\\]](https:\u002F\u002Ficlr.cc\u002Fmedia\u002FSlides\u002Ficlr\u002F2021\u002Fvirtual(05-08-00)-05-08-00UTC-2993-differentiable_.pdf)  [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fdiozaka\u002Fdiffseg) \n* 神经ODE过程 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=27acGyyI1BY) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fcrisbodnar\u002Fndp) \n* 基于随机微分网络学习连续时间动力学 [\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=U850oxFSKmN) [\\[官方代码\\]]() \n\n \n### KDD 2021\n#### 时间序列预测\n* ST-Norm：用于多变量时间序列预测的空间-时间归一化 [\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467330) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FJLDeng\u002FST-Norm)\n* 用于云资源分配的图深度因子预测方法 [\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467357)  \n* 深度时空预测中的不确定性量化 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.11982) \n* 用于交通流量预测的空间-时间图ODE网络 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.12931) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsquare-coder\u002FSTGODE)\n* TrajNet：基于轨迹的交通预测深度学习模型 [\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467236)  \n* 用于交通速度预测的动态多维度时空深度学习 [\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467275) \n\n\n#### 时间序列异常检测\n* 基于层次化指标间与时间嵌入的多变量时间序列异常检测与解释 [\\[论文\\]](https:\u002F\u002Fnetman.aiops.org\u002Fwp-content\u002Fuploads\u002F2021\u002F08\u002FKDD21_InterFusion_Li.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fzhhlee\u002FInterFusion)\n* 异步多变量时间序列异常检测与定位的实用方法 [\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467174) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FeBay\u002FRANSynCoders)\n* 基于神经系统辨识和贝叶斯滤波的网络物理系统时间序列异常检测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07992) [\\[官方代码\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07992)\n* 多尺度单类循环神经网络用于离散事件序列异常检测 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.13361) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fwzwtrevor\u002FMulti-Scale-One-Class-Recurrent-Neural-Networks)\n\n#### 其他时间序列分析\n* 基于Transformer框架的多变量时间序列表征学习 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.02803) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fgzerveas\u002Fmvts_transformer)\n* 用于时间序列分析的因果可解释规则 [\\[论文\\]](https:\u002F\u002Fjosselin-garnier.org\u002Fwp-content\u002Fuploads\u002F2021\u002F10\u002Fkdd21.pdf)  \n* MiniRocket：一种快速（几乎）确定性的时间序列分类变换 [\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.08791) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fangus924\u002Fminirocket)\n* 统计模型耦合可用于复杂的局部多变量时间序列分析 [\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3447548.3467362)\n* 用于时间序列数据的快速且精确的部分傅里叶变换 [\\[论文\\]](https:\u002F\u002Fjungijang.github.io\u002Fresources\u002F2021\u002FKDD\u002Fpft.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsnudatalab\u002FPFT)\n* 用于数据序列相似性搜索的深度学习嵌入 [\\[论文\\]](https:\u002F\u002Fqtwang.github.io\u002Fassets\u002Fpdf\u002Fkdd21-seanet.pdf) [\\[链接\\]](https:\u002F\u002Fqtwang.github.io\u002Fkdd21-seanet)\n\n### AAAI 2021\n#### 时间序列预测\n* Informer：超越高效Transformer的长序列时间序列预测 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.07436) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fzhouhaoyi\u002FInformer2020)\n* 深度切换自回归分解模型：应用于时间序列预测 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.05135) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fostadabbas\u002FDSARF)\n* 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鲁棒预测 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.02164) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fthuwuyinjun\u002FDGM2)\n* 时间潜变量自编码器：一种概率性多变量时间序列预测方法 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.10460)\n* 异构时间序列的协同学习，用于多步长概率预测 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.00431)\n* 元学习框架及其在零样本时间序列预测中的应用 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.02887)\n* 注意力神经点过程用于事件预测 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16929) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fguyulongcs\u002FAAAI2021_ANPP)\n* 基于循环神经ODE的水库入流量预测 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17763)\n* 用于交通流量预测的层次图卷积网络 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16088)\n* 基于时空图扩散网络的交通流量预测 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.04038) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjillbetty001\u002FST-GDN)\n* 用于交通流量预测的时空融合图神经网络 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.09641) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002FMengzhangLI\u002FSTFGNN)\n* FC-GAGA：用于时空交通预测的全连接门控图架构 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.15531) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fboreshkinai\u002Ffc-gaga)\n* 预测与线性动力系统学习中的公平性 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.07315)\n* 基于立方体扰动的多步马尔可夫条件前向模型，用于极端天气预报 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16856)\n* 基于机器学习的次季节气候预测：挑战、分析与进展 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16090)\n\n#### 时间序列异常检测\n* 基于图神经网络的多变量时间序列异常检测 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06947) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fd-ailin\u002FGDN)\n* 多分辨率集成解码的时间序列异常检测 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17152)\n* 时间序列数据的离群值影响特征化 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17379)\n\n#### 时间序列分类\n* 相关通道感知融合用于多视角时间序列分类 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16830\u002F16637)\n* 可学习的动态时间池化用于时间序列分类 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.02577) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fdonalee\u002FDTW-Pool)\n* ShapeNet：基于形状子神经网络的多变量时间序列分类方法 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17018)\n* 双重增强联合标签学习用于时间序列分类 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17071)\n\n#### 其他时间序列分析\n* 基于稀疏关联结构对齐的时间序列领域适应 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.11797) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002FDMIRLAB-Group\u002FSASA)\n* 不完全时间序列聚类的表示学习 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17070)\n* 用于多变量时间序列插补的生成式半监督学习 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17086) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fzjuwuyy-DL\u002FGenerative-Semi-supervised-Learning-for-Multivariate-Time-Series-Imputation)\n* 用于学习具有结构突变的时间序列的二阶技术 [\\[:论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17117)\n\n\n\n### IJCAI 2021\n#### 时间序列预测\n* 一石二鸟：序列显著性用于准确且可解释的多变量时间序列预测 [\\[:论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F397)\n* 基于图神经网络注意力迁移的居民用电负荷预测 [\\[:论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F374)\n* 用于股票趋势预测的层次自适应时序关系建模 [\\[:论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0508.pdf)\n* TrafficStream：基于图神经网络和持续学习的流式交通流量预测框架 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06273) [\\[:官方代码\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06273)\n\n#### 其他时间序列分析\n* 面向深度学习的时间序列数据增强：综述 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12478)\n* 基于时间和上下文对比的时间序列表示学习 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.14112) [\\[:官方代码\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.14112)\n* 非监督时间序列领域适应的对抗性谱核匹配 [\\[:论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F378) [\\[:官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjarheadjoe\u002FAdv-spec-ker-matching)\n* 适用于时间序列建模的时间感知多尺度RNN [\\[:论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F315)\n* TE-ESN：基于不规则采样时间序列数据的时序编码回声状态网络预测 [\\[:论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.00412)\n\n\n\u003C!--  [\\[论文\\]]() [\\[官方代码\\]]()  -->\n\n### SIGMOD VLDB ICDE 2021\n#### 时间序列预测\n* AutoAI-TS：面向时间序列预测的AutoAI，SIGMOD'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.12347)  \n* FlashP：用于实时预测时间序列关系数据的分析流水线，VLDB'21。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp721-ding.pdf)\n* MDTP：一种基于时空轨迹数据的多源深度交通预测框架，VLDB'21。[\\[论文\\]]()\n* EnhanceNet：用于增强相关性时间序列预测的插件神经网络，ICDE'21。[\\[论文\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9458855) [\\[幻灯片\\]](https:\u002F\u002Fpdfs.semanticscholar.org\u002F3cb0\u002F6f67fbfcf3c2dac32c02248a03eb84cc246d.pdf)  \n* 一种有效的出行需求与交通流量联合预测模型，ICDE'21。[\\[论文\\]](https:\u002F\u002Fdbgroup.cs.tsinghua.edu.cn\u002Fligl\u002Fpapers\u002Ficde21-traffic.pdf)  \n\n#### 时间序列异常检测\n* Exathlon：面向时间序列可解释异常检测的基准测试，VLDB'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.05073) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fexathlonbenchmark\u002Fexathlon)\n* SAND：流式子序列异常检测，VLDB'21。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp1717-boniol.pdf)  \n\n#### 其他时间序列分析\n* RobustPeriod：鲁棒的时频挖掘用于多周期性检测，SIGMOD'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.09535) [\\[代码\\]](https:\u002F\u002Fgithub.com\u002Fariaghora\u002Frobust-period)\n* ORBITS：多时间序列流中缺失值的在线恢复，VLDB'21。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp294-khayati.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FeXascaleInfolab\u002Forbits)\n* 多维时间序列中的缺失值填补，VLDB'21。[\\[论文\\]](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp2533-bansal.pdf) \n\n\u003C!--    , WSDM'21. [\\[论文\\]]() [\\[官方代码\\]]()   --> \n### 杂项 2021\n#### 时间序列预测\n* DeepFEC：面向智慧城市的实际驾驶条件下能耗预测，WWW'21。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3442381.3449983) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FElmiSay\u002FDeepFEC)\n* AutoSTG：用于时空图预测的神经架构搜索，WWW'21。[\\[论文\\]](http:\u002F\u002Fpanzheyi.cc\u002Fpublication\u002Fpan2021autostg\u002Fpaper.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fpanzheyi\u002FAutoSTG)\n* REST：时空耦合预测的互惠框架，WWW'21。[\\[论文\\]](https:\u002F\u002Fs2.smu.edu\u002F~jiazhang\u002FPapers\u002FJiaZhang-WWW2021-REST.pdf)\n* 分层相关时间序列的同步分位数预测，AISTATS'21。[\\[论文\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv130\u002Fhan21a\u002Fhan21a.pdf)  \n* SSDNet：用于时间序列预测的状态空间分解神经网络，ICDM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.10251)  \n* AdaRNN：时间序列的自适应学习与预测，CIKM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.04443) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjindongwang\u002Ftransferlearning\u002Ftree\u002Fmaster\u002Fcode\u002Fdeep\u002Fadarnn)\n* 学习预测未来：时间序列预测中的概念漂移建模，CIKM'21。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3459637.3482271)  \n* 基于多粒度数据的股票趋势预测：一种带有自适应融合的对比学习方法，CIKM'21。[\\[论文\\]](http:\u002F\u002Fstaff.ustc.edu.cn\u002F~cheneh\u002Fpaper_pdf\u002F2021\u002FMin-Hou-CIKM.pdf)  \n* DL-Traff：城市交通预测深度学习模型综述与基准测试，CIKM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.09091) [\\[官方代码1\\]](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002Fdl-traff-graph) [\\[官方代码2\\]](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002Fdl-traff-grid)\n* 基于时间点过程的长 horizon 预测，WSDM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.02815) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fpratham16cse\u002FDualTPP)\n* 基于演化状态图的时间序列事件预测，WSDM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05006) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FVachelHU\u002FEvoNet)。\n\n#### 时间序列异常检测\n* SDFVAE：用于多变量CDN KPI异常检测的静态与动态因子化VAE，WWW'21。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3442381.3450013) \n* 基于自监督对比预测编码的时间序列变点检测，WWW'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.14097) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fcruiseresearchgroup\u002FTSCP2)\n* FluxEV：一种快速有效的无监督时间序列异常检测框架，WSDM'21。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3437963.3441823) \n* 基于动态时间规整的弱监督时间序列异常分割，ICCV'21。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3437963.3441823) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fdonalee\u002Fwetas)\n* 面向在线服务系统的多变量时间序列异常检测的快速启动，ATC'21。[\\[论文\\]](https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fatc21\u002Fpresentation\u002Fma)\n\n\n\n#### 其他时间序列分析\n* 张量时间序列网络，WWW'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07736) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FNET3)\n* Radflow：一种用于时间序列网络的循环、聚合与分解模型，WWW'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07289) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Falasdairtran\u002Fradflow)\n* SrVARM：状态正则化的向量自回归模型，用于从多变量时间序列中联合学习隐藏状态转移和状态依赖的变量间依赖关系，WWW'21。[\\[论文\\]](https:\u002F\u002Ffaculty.ist.psu.edu\u002Fvhonavar\u002FPapers\u002FSRVARM.pdf)  \n* 用于自注意力点过程的深度傅里叶核，AISTATS'21。[\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv130\u002Fzhu21b.html)\n* 时间序列之间的可微散度，AISTATS'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08354) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fsoft-dtw-divergences) \n* 在不可比较空间上对齐时间序列，AISTATS'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.12648) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsamcohen16\u002FAligning-Time-Series) \n* 针对输入维度可变的多变量时间序列任务的持续学习，ICDM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.06852)  \n* 向生成真实世界时间序列数据迈进，ICDM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.08386) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Facphile\u002FRTSGAN)\n* 学习显著性图以解释深度时间序列分类器，CIKM'21。[\\[论文\\]](https:\u002F\u002Fkingspp.github.io\u002Fpublications\u002F) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fkingspp\u002Ftimeseries-explain)\n* 城市多变量时间序列中的可操作洞察，CIKM'21。[\\[论文\\]](https:\u002F\u002Fpeople.cs.vt.edu\u002Fanikat1\u002Fpublications\u002Fratss-cikm2021.pdf) \n* 可解释的多变量时间序列分类：一种能够同时关注重要变量和信息丰富时段的深度神经网络，WSDM'21。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.11631)  \n\n\n## AI4TS 论文 201X-2020 精选\n\n### NeurIPS 201X-2020\n\n#### 时间序列预测\n* 面向时间序列预测的对抗稀疏Transformer，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002F\u002Fpaper\u002F2020\u002Ffile\u002Fc6b8c8d762da15fa8dbbdfb6baf9e260-Paper.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fhihihihiwsf\u002FAST) \n* 用于多变量时间序列预测的谱时空图神经网络，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.07719) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FStemGNN) \n* 用于时间序列预测的深度Rao-Blackwell化粒子滤波器，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002Fafb0b97df87090596ae7c503f60bb23f-Abstract.html) \n* 基于形状和时间多样性的概率性时间序列预测，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.07349) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fvincent-leguen\u002FSTRIPE) \n* 用于交通流量预测的自适应图卷积循环网络，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.02842) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FLeiBAI\u002FAGCRN) \n* 用于新冠肺炎预测的可解释序列学习，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.00646) \n* 提升Transformer在时间序列预测中的局部性并突破内存瓶颈，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.00235) [\\[代码\\]](https:\u002F\u002Fgithub.com\u002Fmlpotter\u002FTransformer_Time_Series) \n* 全局思考，局部行动：一种用于高维时间序列预测的深度神经网络方法，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.03806) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Frajatsen91\u002Fdeepglo) \n* 使用低秩高斯Copula过程进行高维多变量预测，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.03002) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmbohlkeschneider\u002Fgluon-ts) \n* 用于时间序列预测的深度状态空间模型，NeurIPS'18。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2018\u002Fhash\u002F5cf68969fb67aa6082363a6d4e6468e2-Abstract.html)  \n* 用于高维时间序列预测的时序正则化矩阵分解，NeurIPS'16。[\\[论文\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2016\u002Fhash\u002F85422afb467e9456013a2a51d4dff702-Abstract.html)  \n\n#### 时间序列异常检测\n* 基于时序层次单类网络的时间序列异常检测，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F97e401a02082021fd24957f852e0e475-Abstract.html)  \n* PIDForest：通过部分识别进行异常检测，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.03582) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fvatsalsharan\u002Fpidforest) \n* 时间序列的精确率与召回率，NeurIPS'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1803.03639) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FIntelLabs\u002FTSAD-Evaluator) \n\n#### 时间序列分类\n* 浅层RNN：在资源受限设备上实现准确的时间序列分类，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Fhash\u002F76d7c0780ceb8fbf964c102ebc16d75f-Abstract.html)  \n#### 时间序列聚类\n* 用于时间序列聚类的表示学习，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2019\u002Fhash\u002F1359aa933b48b754a2f54adb688bfa77-Abstract.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fqianlima-lab\u002FDTCR) \n* 从时间序列数据中学习低维状态嵌入和亚稳态簇，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.00302)\n\n#### 时间序列插补\n* NAOMI：非自回归多分辨率序列插补，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.10946) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Ffelixykliu\u002FNAOMI) \n* BRITS：面向时间序列的双向递归插补，NeurIPS'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.10572) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fcaow13\u002FBRITS) \n* 使用生成对抗网络进行多变量时间序列插补，NeurIPS'18。[\\[论文\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2018\u002Fhash\u002F96b9bff013acedfb1d140579e2fbeb63-Abstract.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FLuoyonghong\u002FMultivariate-Time-Series-Imputation-with-Generative-Adversarial-Networks) \n\n#### 时间序列神经xDE\n* 用于不规则时间序列的神经控制微分方程，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.08926) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fpatrick-kidger\u002FNeuralCDE)  \n* GRU-ODE-Bayes：对零星观测的时间序列进行连续建模，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.12374) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fedebrouwer\u002Fgru_ode_bayes)  \n* 用于不规则采样时间序列的潜在常微分方程，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.03907) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FYuliaRubanova\u002Flatent_ode)  \n* 神经常微分方程，NeurIPS'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.07366) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Frtqichen\u002Ftorchdiffeq)  \n\n#### 时间序列通用分析\n* 对具有潜在混杂因素的自相关时间序列进行高召回率的因果发现，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F94e70705efae423efda1088614128d0b-Abstract.html) [\\[论文2\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.01884) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjakobrunge\u002Ftigramite) \n* 时间序列预测中深度学习可解释性的基准测试，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.13924) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fayaabdelsalam91\u002FTS-Interpretability-Benchmark)\n* 出了什么问题？什么时候出的问题？针对时间序列黑箱模型的实例级特征重要性，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.02821) [\\[官方代码\\]]()\n* 用于多变量时间序列分析的归一化卡尔曼滤波器，NeurIPS'20。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Fhash\u002F1f47cef5e38c952f94c5d61726027439-Abstract.html)\n* 用于多变量时间序列的无监督可扩展表示学习，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.10738) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FWhite-Link\u002FUnsupervisedScalableRepresentationLearningTimeSeries)\n* 时间序列生成对抗网络，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2019\u002Fhash\u002Fc9efe5f26cd17ba6216bbe2a7d26d490-Abstract.html) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjsyoon0823\u002FTimeGAN) \n* U-Time：一种应用于睡眠分期的时间序列分割全卷积网络，NeurIPS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.11162) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fperslev\u002FU-Time) \n* Autowarp：利用序列自编码器从无标签时间序列中学习变形距离，NeurIPS'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.10107)\n* 基于高斯过程的时间序列建模的安全主动学习，NeurIPS'18。[\\[论文\\]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2018\u002Fhash\u002Fb197ffdef2ddc3308584dce7afa3661b-Abstract.html)\n\n### ICML 201X-2020\n\n#### 通用时间序列分析\n* 从不规则采样时间序列中学习：基于缺失数据的视角，ICML'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.07599) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsteveli\u002Fpartial-encoder-decoder)\n* 时间序列的集合函数，ICML'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.12064) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FBorgwardtLab\u002FSet_Functions_for_Time_Series)\n* 时间序列去混杂器：在存在隐藏混杂因素的情况下估计随时间变化的治疗效应，ICML'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00450) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FTime-Series-Deconfounder)\n* 平稳时间序列的谱子采样MCMC，ICML'20。[\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fsalomone20a.html)\n* 时间序列的可学习分组变换，ICML'20。[\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fcosentino20a.html)\n* 基于状态空间模型的非平稳环境中的因果发现与预测，ICML'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.10857) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FBiwei-Huang\u002FCausal-discovery-and-forecasting-in-nonstationary-environments)\n* 发现多时间序列的潜在协方差结构，ICML'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.09528)\n* 用于异步时间序列的自回归卷积神经网络，ICML'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.04122) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmbinkowski\u002Fnntimeseries)\n* 用于多速率多变量时间序列的层次化深度生成模型，ICML'18。[\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fche18a.html)\n* 软DTW：一种针对时间序列的可微损失函数，ICML'17。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.01541) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmblondel\u002Fsoft-dtw)\n\n\n#### 时间序列预测\n* 使用一致Koopman自编码器进行序列数据预测，ICML'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.02236) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Ferichson\u002FkoopmanAE)\n* 对概率自回归预测模型的对抗攻击，ICML'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.03778) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Feth-sri\u002Fprobabilistic-forecasts-attacks)\n* 基于高斯过程的流感预测框架，ICML'20。[\\[论文\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fzimmer20a.html)\n* 用于预测的深度因子，ICML'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.12417)\n* 层次化时间序列的一致性概率预测，ICML'17。[\\[论文\\]](https:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Ftaieb17a.html)\n\n### ICLR 201X-2020\n#### 通用时间序列分析\n* 用于不规则采样时间序列的插值-预测网络，ICLR'19。[\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1efr3C9Ym) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmlds-lab\u002Finterp-net)\n* SOM-VAE：时间序列上的可解释离散表征学习，ICLR'19。[\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=rygjcsR9Y7) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fratschlab\u002FSOM-VAE)\n\n#### 时间序列预测\n* N-BEATS：用于可解释时间序列预测的神经基扩展分析，ICLR'20。[\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1ecqn4YwB) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FElementAI\u002FN-BEATS)\n* 扩散卷积循环神经网络：数据驱动的交通流量预测，ICLR'18。[\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=SJiHXGWAZ) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fliyaguang\u002FDCRNN)\n* 自动推断时空预测中的数据质量，ICLR'18。[\\[论文\\]](https:\u002F\u002Fopenreview.net\u002Fforum?id=ByJIWUnpW)\n\n### KDD 201X-2020\n\n#### 通用时间序列分析\n* Fast RobustSTL：针对具有复杂模式的时间序列的高效稳健季节性趋势分解，KDD'20。[\\[论文\\]](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FQingsong-Wen\u002Fpublication\u002F343780200_Fast_RobustSTL_Efficient_and_Robust_Seasonal-Trend_Decomposition_for_Time_Series_with_Complex_Patterns\u002Flinks\u002F614b9828a3df59440ba498b3\u002FFast-RobustSTL-Efficient-and-Robust-Seasonal-Trend-Decomposition-for-Time-Series-with-Complex-Patterns.pdf) [\\[代码\\]](https:\u002F\u002Fgithub.com\u002Fariaghora\u002Ffast-robust-stl)\n* 基于弱监督的多源深度域适应方法在时间序列传感器数据中的应用，KDD'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.10996) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Ffloft\u002Fcodats)\n* 在线遗忘型DTW算法用于实时黄金批次监控，KDD'19。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330650)\n* 多级小波分解网络用于可解释的时间序列分析，KDD'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.08946)\n* 基于托普利茨逆协方差矩阵的多元时间序列数据聚类，KDD'17。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.03161)\n\n\n#### 时间序列预测\n* 连接各点：基于图神经网络的多元时间序列预测，KDD'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11650) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FMTGNN)\n* 基于注意力机制的多模态新产品销售时间序列预测，KDD'20。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3394486.3403362)\n* 水电发电量演变趋势预测，KDD'20。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3394486.3403337)\n* 时间序列预测中极端事件建模，KDD'19。[\\[论文\\]](http:\u002F\u002Fstaff.ustc.edu.cn\u002F~hexn\u002Fpapers\u002Fkdd19-timeseries.pdf)\n* 基于时序注意力学习的多步长时间序列预测，KDD'19。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330662)\n* 无需无偏条件的分层预测正则化回归，KDD'19。[\\[论文\\]](https:\u002F\u002Fsouhaib-bentaieb.com\u002Fpapers\u002F2019_kdd_hts_reg.pdf)\n* 使用自适应循环单元对深度预测模型进行流式适应，KDD'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.09926) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fpratham16\u002FARU)\n* 针对随时间演化的数据流的动态建模与预测，KDD'19。[\\[论文\\]](https:\u002F\u002Fwww.dm.sanken.osaka-u.ac.jp\u002F~yasuko\u002FPUBLICATIONS\u002Fkdd19-orbitmap.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fyasuko-matsubara\u002Forbitmap)\n* DeepUrbanEvent：用于预测大型活动期间城市范围人群动态的系统，KDD'19。[\\[论文\\]](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FRenhe-Jiang\u002Fpublication\u002F334714928_DeepUrbanEvent_A_System_for_Predicting_Citywide_Crowd_Dynamics_at_Big_Events\u002Flinks\u002F5d417167299bf1995b597f28\u002FDeepUrbanEvent-A-System-for-Predicting-Citywide-Crowd-Dynamics-at-Big-Events.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fdeepkashiwa20\u002FDeepUrbanEvent)\n* 通过发现多频交易模式进行股票价格预测，KDD'17。[\\[论文\\]](https:\u002F\u002Fwww.eecs.ucf.edu\u002F~gqi\u002Fpublications\u002Fkdd2017_stock.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fz331565360\u002FState-Frequency-Memory-stock-prediction)\n\n#### 时间序列异常检测\n* USAD：面向多元时间序列的无监督异常检测，KDD'20。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3394486.3403392) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fmanigalati\u002Fusad)\n* RobustTAD：基于分解和卷积神经网络的稳健时间序列异常检测，KDD'20 MiLeTS。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.09545)\n* 通过随机递归神经网络实现的多元时间序列稳健异常检测，KDD'19。[\\[论文\\]](https:\u002F\u002Fnetman.aiops.org\u002Fwp-content\u002Fuploads\u002F2019\u002F08\u002FOmniAnomaly_camera-ready.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002FOmniAnomaly)\n* 微软公司的时间序列异常检测服务，KDD'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03821)\n* 利用LSTM和非参数动态阈值法检测航天器异常，KDD'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.04431) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fkhundman\u002Ftelemanom)\n* 基于极值理论的流式异常检测，KDD'17。[\\[论文\\]](https:\u002F\u002Fhal.archives-ouvertes.fr\u002Fhal-01640325\u002Fdocument)\n\n### AAAI 201X-2020\n\n#### 通用时间序列分析\n* Time2Graph：利用动态形状子串重新审视时间序列建模，AAAI'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.04143) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fpetecheng\u002FTime2Graph) \n* DATA-GRU：用于不规则多变量时间序列的双注意力时序感知门控循环单元，AAAI'20。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5440)\n* 带自适应共享记忆的张量化LSTM用于学习多变量时间序列中的趋势，AAAI'20。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5496) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FDerronXu\u002FDeepTrends) \n* 不完全多模态时间序列中深度马尔可夫模型的因子化推理，AAAI'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.13570) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fztangent\u002Fmultimodal-dmm) \n* 基于度量学习的智能建筑中传感器时间序列间关系推断，AAAI'20。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5900) \n* TapNet：基于注意力原型网络的多变量时间序列分类，AAAI'20。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6165) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fxuczhang\u002Ftapnet) \n* RobustSTL：一种适用于长时序数据的鲁棒季节性-趋势分解方法，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4480) [\\[代码\\]](https:\u002F\u002Fgithub.com\u002FLeeDoYup\u002FRobustSTL)\n* 从部分观测时间序列中估计因果效应，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4281)\n* 针对活动时间序列的对抗式无监督表示学习，AAAI'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.06847)\n* 时间序列建模中周期核函数的傅里叶特征近似，AAAI'18。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11696)\n\n#### 时间序列预测\n* 结合局部与全局时序动态的多变量时间序列缺失值预测，AAAI'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.10273)  \n* 块汉克尔张量ARIMA用于多个短时序预测，AAAI'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12135) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fyokotatsuya\u002FBHT-ARIMA) \n* 空间-时间同步图卷积网络：一种新的时空网络数据预测框架，AAAI'20。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5438) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FDavidham3\u002FSTSGCN) \n* 自注意力ConvLSTM用于时空预测，AAAI'20。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6819) \n* 多范围注意力双组件图卷积网络用于交通流量预测，AAAI'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.12093)  \n* 用于交通流量预测的空间-时间图结构学习，AAAI'20。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5470) \n* GMAN：一种用于交通预测的图多注意力网络，AAAI'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.08415) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fzhengchuanpan\u002FGMAN) \n* Cogra：面向时间序列预测的概念漂移感知随机梯度下降法，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4383)  \n* 用于交通预测的动态空间-时间图卷积神经网络，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3877) \n* 基于注意力的空间-时间图卷积网络用于交通流预测，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002F\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3881) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FguoshnBJTU\u002FASTGCN-r-pytorch)\n* MRes-RGNN：一种新颖的基于深度学习的交通预测框架，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3821)\n* DeepSTN+：上下文感知的空间-时间神经网络用于大都市人群流动预测，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3892) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FFIBLAB\u002FDeepSTN)\n* 面向时空事件子类型预测的不完全标签多任务深度学习，AAAI'19。[\\[论文\\]](http:\u002F\u002Fcs.emory.edu\u002F~lzhao41\u002Fmaterials\u002Fpapers\u002Fmain_AAAI2019.pdf) \n* 学习异质性空间-时间表征以预测共享单车需求，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3890)  \n* 用于网约车需求预测的空间-时间多图卷积网络，AAAI'19。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002F\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4247) \n\n#### 时间序列异常检测\n* 用于多变量时间序列数据无监督异常检测与诊断的深度神经网络，AAAI'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.08055)\n* 多时间序列中的非参数异常点检测——以电网数据分析为例，AAAI'18。[\\[论文\\]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F11632)\n\n### IJCAI 201X-2020\n\n#### 通用时间序列分析\n* RobustTrend：一种结合一阶和二阶差分正则化的Huber损失函数，用于时间序列趋势滤波，IJCAI'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03751) \n* E2GAN：端到端生成对抗网络，用于多变量时间序列插补，IJCAI'19。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0429.pdf)\n* 基于监督学习的时间序列因果推断，IJCAI'18。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F282)\n\n#### 时间序列预测\n* PewLSTM：具有天气感知门控机制的周期性LSTM，用于停车行为预测，IJCAI'20。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F610) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FNingxuanFeng\u002FPewLSTM)\n* LSGCN：基于图卷积网络的长短期交通流量预测，IJCAI'20。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F326)\n* 用于城市异常事件预测的交叉交互层次化注意力网络，IJCAI'20。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F601)\n* 学习可解释的深度状态空间模型，用于概率型时间序列预测，IJCAI'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.00397)\n* 用于多变量时间序列预测的可解释深度神经网络，IJCAI'19。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F932)\n* Periodic-CRN：一种用于预测具有周期性模式的人群密度的卷积循环模型。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F519)\n* 空间-时间图卷积网络：一种用于交通流量预测的深度学习框架。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1709.04875) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FVeritasYin\u002FSTGCN_IJCAI-18)\n* LC-RNN：一种用于交通速度预测的深度学习模型。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F482)\n* GeoMAN：用于地理传感时间序列预测的多级注意力网络，IJCAI'18。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F476) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fyoshall\u002FGeoMAN)\n* 针对用电模式分析与聚合一致性整合的层次化电力时间序列预测，IJCAI'18。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2018\u002F487)\n* NeuCast：电网时间序列的季节性神经网络预测，IJCAI'18。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F460) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fchenpudigege\u002FNeuCast)\n* 用于时间序列预测的双阶段基于注意力的循环神经网络，IJCAI'17。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.02971) [\\[代码\\]](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fa-dual-stage-attention-based-recurrent-neural)\n* 用于学习时间序列趋势的混合神经网络，IJCAI'17。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2017\u002F316)\n\n#### 时间序列异常检测\n* BeatGAN：利用对抗生成时间序列进行异常节律检测，IJCAI'19。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F616) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fhi-bingo\u002FBeatGAN) \n* 基于循环自编码器集成的时间序列异常检测，IJCAI'19。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F378) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Ftungk\u002FOED) \n* 流式时间序列的随机在线异常分析，IJCAI'17。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2017\u002F0445.pdf)\n\n\n#### 时间序列聚类\n* 基于符号模式森林的线性时间复杂度时间序列聚类，IJCAI'19。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F406)\n* 用于时间序列聚类的相似性保持表示学习，IJCAI'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1702.03584)\n\n\n#### 时间序列分类\n* 一种用于多变量时间序列分类的新注意力机制，IJCAI'20。[\\[论文\\]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F277)\n\n \n### SIGMOD VLDB ICDE 201X-2020\n#### 通用时间序列分析\n* 揭穿关于时间序列距离度量的四个长期误解，SIGMOD'20。[\\[论文\\]](http:\u002F\u002Fpeople.cs.uchicago.edu\u002F~jopa\u002FPapers\u002FPaparrizosSIGMOD2020.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fjohnpaparrizos\u002FTSDistEval) \n* 利用时间序列分析和机器学习进行数据库工作负载容量规划，SIGMOD'20。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3318464.3386140) \n* 注意差距：时间序列中缺失值插补技术的实验评估，VLDB'20。[\\[论文\\]](http:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol13\u002Fp768-khayati.pdf) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FeXascaleInfolab\u002Fbench-vldb20) \n* 用于正例未标记时间序列分类的主动模型选择，ICDE'20。[\\[论文\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9101367) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fsliang11\u002FActive-Model-Selection-for-PUTSC) \n* ExplainIt! -- 一种用于时间序列数据的声明式根本原因分析引擎，SIGMOD'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.08132) \n* Cleanits：一种用于工业时间序列的数据清洗系统，VLDB'19。[\\[论文\\]](https:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol12\u002Fp1786-ding.pdf) \n* Matrix Profile X：VALMOD - 可扩展地发现数据序列中的变长模式，SIGMOD'18。[\\[论文\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fpublications\u002Fsigmod18-valmod.pdf) \n* 有效发现时间序列数据中的时序依赖关系，VLDB'18。[\\[论文\\]](https:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol11\u002Fp893-cai.pdf) \n\n#### 时间序列异常检测\n* Series2Graph：基于图的子序列异常检测方法，用于时间序列，VLDB'20。[\\[论文\\]](http:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol13\u002Fp1821-boniol.pdf) [\\[官方代码\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fseries2graph\u002F) \n* Neighbor Profile：无监督时间序列挖掘中的近邻袋装法，ICDE'20。[\\[论文\\]](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FYuanduo-He\u002Fpublication\u002F340663191_Neighbor_Profile_Bagging_Nearest_Neighbors_for_Unsupervised_Time_Series_Mining\u002Flinks\u002F5e97d607a6fdcca7891c2a0b\u002FNeighbor-Profile-Bagging-Nearest-Neighbors-for-Unsupervised-Time-Series-Mining.pdf)  \n* 大规模序列中的自动化异常检测，ICDE'20。[\\[论文\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fpublications\u002Ficde20-norm.pdf) [\\[官方代码\\]](https:\u002F\u002Fhelios2.mi.parisdescartes.fr\u002F~themisp\u002Fnorm\u002F) \n* 用户驱动的带事件的时间序列错误检测，ICDE'20。[\\[论文\\]](https:\u002F\u002Fwww.eurecom.fr\u002Fen\u002Fpublication\u002F6192\u002Fdownload\u002Fdata-publi-6192.pdf)\n\n\n\u003C!--    , Misc'20. [\\[论文\\]]() [\\[官方代码\\]]()   WWW, AISTAT, CIKM, ICDM, WSDM, SIGIR, ATC, etc. -->\n\n### 杂项 201X-2020\n#### 通用时间序列分析\n* STFNets：基于短时傅里叶神经网络的时间—频域感知信号学习，WWW'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.07849) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fyscacaca\u002FSTFNets)\n* GP-VAE：深度概率时间序列插补，AISTATS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.04155) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Fratschlab\u002FGP-VAE)\n* DYNOTEARS：基于时间序列数据的结构学习，AISTATS'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.00498)\n* 基于知识迁移的可穿戴传感器时间序列个性化插补，CIKM'20。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3340531.3411879)\n* 用于多变量时间序列挖掘的保序度量学习，ICDM'20。[\\[论文\\]](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10233687)\n* 从不完整多变量时间序列中学习周期，ICDM'20。[\\[论文\\]](http:\u002F\u002Fwww.cs.albany.edu\u002F~petko\u002Flab\u002Fpapers\u002Fzgzb2020icdm.pdf)\n* 时间序列序列到序列建模的基础，AISTATS'19。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.03714)\n\n#### 时间序列预测\n* 用于细粒度空间事件预测的层次化Transformer网络，WWW'20。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3366423.3380296)\n* HTML：基于层次化Transformer的波动率预测多任务学习，WWW'20。[\\[论文\\]](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340385140_HTML_Hierarchical_Transformer-based_Multi-task_Learning_for_Volatility_Prediction) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FYangLinyi\u002FHTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction)\n* 基于时空图神经网络的交通流量预测，WWW'20。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380186)\n* 向细粒度流量预测迈进：一种用于共享单车系统的图注意力方法，WWW'20。[\\[论文\\]](https:\u002F\u002Fuconnuclab.github.io\u002Fpublications\u002F2020\u002FConference\u002Fhe-www-2020-a.pdf)\n* 用于金融预测的领域自适应多模态神经注意力网络，WWW'20。[\\[论文\\]](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10161328)\n* 用于股票走势预测的时空超图卷积网络，ICDM'20。[\\[论文\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338303)\n* 基于样条分位函数RNN的概率预测，AISTATS'19。[\\[论文\\]](http:\u002F\u002Fproceedings.mlr.press\u002Fv89\u002Fgasthaus19a.html)\n* DSANet：用于多变量时间序列预测的双自注意力网络，CIKM'19。[\\[论文\\]](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3358132)\n* RESTFul：面向行为时间序列数据的分辨率感知预测，CIKM'18。[\\[论文\\]](https:\u002F\u002Fwww3.nd.edu\u002F~dial\u002Fpublications\u002Fxian2018restful.pdf)\n* 基于注意力神经网络的波形变换时间序列预测，ICDM'18。[\\[论文\\]](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8595010)\n* 一种适用于具有季节性模式的层次化时间序列的灵活预测框架：以Web流量为例，SIGIR'18。[\\[论文\\]](https:\u002F\u002Fpeople.cs.pitt.edu\u002F~milos\u002Fresearch\u002F2018\u002FSIGIR_18_Liu_Hierarchical_Seasonal_TS.pdf)\n* 使用深度神经网络建模长短期时间模式，SIGIR'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.07015) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002Flaiguokun\u002FLSTNet)\n\n#### 时间序列异常检测\n* 基于图注意力网络的多变量时间序列异常检测，ICDM'20。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.02040) [\\[代码\\]](https:\u002F\u002Fgithub.com\u002FML4ITS\u002Fmtad-gat-pytorch)\n* MERLIN：在海量时间序列档案中无参数发现任意长度异常，ICDM'20。[\\[论文\\]](https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002FMERLIN_Long_version_for_website.pdf) [\\[官方代码\\]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fmerlin-find-anomalies\u002FMERLIN)\n* 面向云系统的跨数据集时间序列异常检测，ATC'19。[\\[论文\\]](https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fatc19\u002Fpresentation\u002Fzhang-xu)\n* 基于变分自编码器的无监督异常检测，用于Web应用中的季节性KPI，WWW'18。[\\[论文\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.03903) [\\[官方代码\\]](https:\u002F\u002Fgithub.com\u002FNetManAIOps\u002Fdonut)","# awesome-AI-for-time-series-papers 快速上手指南\n\n`awesome-AI-for-time-series-papers` 并非一个需要安装运行的软件库，而是一个**精心整理的学术资源列表**。它汇集了顶级 AI 会议和期刊中关于时间序列分析（AI4TS）的最新论文、教程和综述，且大部分资源附带代码链接。\n\n本指南将指导你如何快速获取并利用这些资源。\n\n## 环境准备\n\n由于本项目本质是一个文档索引，**无需特定的系统环境或依赖包**。你只需要：\n\n*   **操作系统**：任意支持现代浏览器的系统（Windows, macOS, Linux）。\n*   **必备工具**：\n    *   Web 浏览器（推荐 Chrome, Edge 或 Firefox）。\n    *   Git（可选，用于克隆仓库到本地离线阅读）。\n    *   Python 环境（可选，仅当你需要运行列表中具体论文的开源代码时才需要）。\n\n## 获取资源\n\n你可以通过以下两种方式访问该资源列表：\n\n### 方式一：在线浏览（推荐）\n直接访问 GitHub 仓库页面，利用目录结构快速查找最新论文和教程。\n*   **地址**: `https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers`\n\n### 方式二：本地克隆\n如果你希望离线阅读或通过文本编辑器检索内容，可以使用 Git 克隆仓库。\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fqingsongedu\u002Fawesome-AI-for-time-series-papers.git\ncd awesome-AI-for-time-series-papers\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（如 Gitee 镜像，若有）或配置 Git 代理加速。\n\n## 基本使用\n\n本项目的核心用法是**按图索骥**：通过分类目录找到感兴趣的论文，然后跳转至其对应的代码仓库或教程页面。\n\n### 1. 查找最新论文\n打开 `README.md` 文件，滚动至 **\"Main Recent Update Note\"** 部分，查看最近更新的顶会论文（如 ICLR, AAAI, KDD, NeurIPS 等）。\n\n### 2. 定位特定领域资源\n利用 **Table of Contents (目录)** 快速导航到你关心的子领域：\n*   **教程与综述**：查看 `AI4TS Tutorials and Surveys` 章节，适合快速入门或了解前沿进展。\n    *   *示例*：寻找大模型在时间序列中的应用，可查阅 \"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook\"。\n*   **年度论文**：根据年份（2024, 2023...）和会议名称查找具体研究。\n    *   *示例*：查找 2024 年 KDD 会议关于异常检测的论文，请前往 `AI4TS Papers 2024` -> `KDD 2024`。\n\n### 3. 获取代码与复现\n列表中绝大多数论文条目都包含 `[Link]` 或 `[Code]` 标记。\n1.  点击论文标题旁的链接进入论文详情页或 arXiv 页面。\n2.  在描述中寻找指向 GitHub 仓库的链接（通常标记为 \"available code\"）。\n3.  进入具体的代码仓库后，参照该仓库独立的 `README` 进行环境安装和运行。\n\n**使用示例流程：**\n假设你想复现一篇关于“时间序列预测”的最新 Transformer 模型：\n1.  在本项目页面搜索关键词 \"Transformer\" 或浏览 `Surveys` 中的 \"Transformers in Time Series: A Survey\"。\n2.  找到相关论文条目，点击其附带的代码链接。\n3.  跳转到具体代码库，执行类似以下命令（具体以该代码库说明为准）：\n    ```bash\n    git clone \u003C具体论文的代码仓库地址>\n    cd \u003C具体论文目录>\n    pip install -r requirements.txt\n    python train.py --config configs\u002Fexample.yaml\n    ```\n\n通过以上步骤，你可以高效地利用此列表追踪 AI 时间序列领域的最新动态并复现前沿算法。","某金融科技公司的算法团队正致力于研发新一代股票波动率预测模型，急需追踪最新的时序 AI 研究成果以突破现有性能瓶颈。\n\n### 没有 awesome-AI-for-time-series-papers 时\n- **信息搜集效率低下**：研究人员需手动遍历 NeurIPS、KDD、ICLR 等十几个顶级会议的官网，耗时数天才能拼凑出完整的论文列表。\n- **关键资源缺失**：找到论文标题后，往往难以快速定位对应的开源代码实现或官方教程，导致复现成本极高。\n- **前沿动态滞后**：由于缺乏即时更新机制，团队容易错过刚刚被接收的最新论文（如 ICLR'24 或 KDD'23 的新成果），导致研究起点落后于学术界。\n- **领域覆盖不全**：人工搜索容易遗漏时空数据、事件数据等细分领域的交叉研究，造成技术选型视野狭窄。\n\n### 使用 awesome-AI-for-time-series-papers 后\n- **一站式获取资源**：团队直接访问该清单，即可按会议年份（如 2024 AAAI、WWW）快速获取经过筛选的高质量论文、代码链接及配套教程。\n- **复现周期大幅缩短**：每篇条目均标注了可用代码状态，工程师能立即着手验证 SOTA 模型，将原本数周的文献调研压缩至几小时。\n- **同步最新学术进展**：依托其\"ASAP 更新”机制，团队在会议结果公布第一时间就能掌握如 Time Series 和 Temporal Point Processes 领域的最新突破。\n- **拓宽技术视野**：清单涵盖从传统时序到复杂的时空序列数据，帮助团队发现跨领域的创新架构，优化了模型设计思路。\n\nawesome-AI-for-time-series-papers 通过构建权威且实时的知识索引，将科研人员从繁琐的信息检索中解放出来，使其能专注于核心算法的创新与落地。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fqingsongedu_awesome-AI-for-time-series-papers_2feddb27.png","qingsongedu","Qingsong Wen","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fqingsongedu_1f9b5be6.png","Head of AI @ Squirrel AI | AI for Time Series, AI for Education, LLM & Agent | Hiring Interns\u002FFTEs (Seattle, Shanghai, Remote)!","Squirrel Ai Learning","Seattle, WA",null,"https:\u002F\u002Fqingsongedu.github.io","https:\u002F\u002Fgithub.com\u002Fqingsongedu",1602,148,"2026-04-03T17:56:58","MIT",1,"","未说明",{"notes":89,"python":87,"dependencies":90},"该仓库是一个论文、教程和综述的精选列表（Awesome List），本身不包含可执行的源代码或模型，因此没有特定的运行环境、GPU、内存或依赖库要求。用户需根据列表中链接到的具体论文对应的独立代码仓库来配置相应的运行环境。",[],[14,16],[93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"timeseries","timeseries-analysis","timeseries-forecasting","timeseries-prediction","timeseriesclassification","anomalydetection","changepoint-detection","classification","forecasting","missing-data","data-mining","deep-learning","machine-learning","signal-processing","awesome","awesome-list","tutorial","temporal-models","spatio-temporal-analysis","temporal-point-processes","2026-03-27T02:49:30.150509","2026-04-07T22:59:53.898201",[],[]]