[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-yueliu1999--Awesome-Deep-Graph-Clustering":3,"tool-yueliu1999--Awesome-Deep-Graph-Clustering":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",146793,2,"2026-04-08T23:32:35",[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。",108111,"2026-04-08T11:23:26",[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":72,"owner_avatar_url":73,"owner_bio":74,"owner_company":75,"owner_location":76,"owner_email":77,"owner_twitter":78,"owner_website":79,"owner_url":80,"languages":81,"stars":86,"forks":87,"last_commit_at":88,"license":89,"difficulty_score":10,"env_os":90,"env_gpu":91,"env_ram":91,"env_deps":92,"category_tags":95,"github_topics":96,"view_count":32,"oss_zip_url":78,"oss_zip_packed_at":78,"status":17,"created_at":112,"updated_at":113,"faqs":114,"releases":115},5714,"yueliu1999\u002FAwesome-Deep-Graph-Clustering","Awesome-Deep-Graph-Clustering","Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods (papers, codes, and datasets).","Awesome-Deep-Graph-Clustering 是一个专注于深度图聚类领域的开源资源合集，旨在汇集该方向最前沿（SOTA）的研究成果。它系统地整理了相关的学术论文、代码实现以及数据集，为探索复杂网络结构提供了坚实的技术支撑。\n\n在人工智能应用中，如何从无标号的图数据中自动发现节点间的内在联系并将其合理分组，一直是个极具挑战的难题。Awesome-Deep-Graph-Clustering 正是为了解决这一痛点而生，它帮助使用者快速定位高质量的研究文献与可复现的代码，避免了在海量信息中筛选的高昂时间成本。此外，该资源库还紧跟技术潮流，收录了基于大语言模型（LLM）引导的图聚类等新兴架构方法，展现了领域内的最新突破。\n\n这款工具特别适合人工智能研究人员、算法工程师以及高校师生使用。无论是希望深入了解图神经网络聚类机理的学者，还是需要寻找基准代码进行二次开发的开发者，都能从中获得宝贵的参考资源。通过提供清晰的分类索引和详尽的引用指引，Awesome-Deep-Graph-Clustering 致力于成为连接理论研究与工程实践的桥梁，推动社区共同进步。","[python-img]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flanguages\u002Ftop\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering?color=lightgrey\n[stars-img]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering?color=yellow\n[stars-url]: https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering\u002Fstargazers\n[fork-img]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering?color=lightblue&label=fork\n[fork-url]: https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering\u002Fnetwork\u002Fmembers\n[visitors-img]: https:\u002F\u002Fvisitor-badge.glitch.me\u002Fbadge?page_id=yueliu1999.Awesome-Deep-Graph-Clustering\n[adgc-url]: https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering\n\n# ADGC: Awesome Deep Graph Clustering\n\nADGC is a collection of state-of-the-art (SOTA), novel deep graph clustering methods (papers, codes and datasets). Any other interesting papers and codes are welcome. Any problems, please contact yueliu19990731@163.com. If you find this repository useful to your research or work, it is really appreciated to star this repository. :sparkles: If you use our code or the processed datasets in this repository for your research, please cite 2-3 papers in the citation part [here](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering#citation). :heart:\n\n[![Made with Python][python-img]][adgc-url]\n[![GitHub stars][stars-img]][stars-url]\n[![GitHub forks][fork-img]][fork-url]\n[![visitors][visitors-img]][adgc-url]\n\n--------------\n\n## What is Deep Graph Clustering?\n\nDeep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different groups, has attracted intensive attention in recent years. More details can be found in the survey paper. [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.12875)\n\n\u003Cdiv align=\"center\"> \n \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyueliu1999_Awesome-Deep-Graph-Clustering_readme_feec4e5d784c.png\" width=90% \u002F>\n\u003C\u002Fdiv>\n\n\n\n## Important Survey Papers\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :---------: | :----------------------------------------------------------: | :--: |\n| 2023 | **An Overview of Advanced Deep Graph Node Clustering** | TCSS | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10049408) | - |\n| 2022 | **A Survey of Deep Graph Clustering: Taxonomy, Challenge, and Application** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.12875) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering) |\n| 2022 | **A Comprehensive Survey on Community Detection with Deep Learning** | TNNLS | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2105.12584.pdf?ref=https:\u002F\u002Fgithubhelp.com) | - |\n| 2020 | **A Comprehensive Survey on Graph Neural Networks** | TNNLS | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9046288) | - |\n| 2020 | **Deep Learning for Community Detection: Progress, Challenges and Opportunities** | IJCAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.08225) | - |\n| 2018 | **A survey of clustering with deep learning: From the perspective of network architecture** | IEEE Access | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=8412085) | - |\n\n\n\n\n\n## Papers\n\n### LLM-based Deep Graph Clustering\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ |:-----:| :----------------------------------------------------------: |:----:|\n| 2024 | **Large Language Model Guided Graph Clustering** | LOG | [Link](https:\u002F\u002Fopenreview.net\u002Fpdf?id=CLyhlb5DG5) | - |\n\n\n### New-architecture Deep Graph Clustering\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **Expander Hierarchies for Normalized Cuts on Graphs** | KDD |[link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3637528.3671978) | https:\u002F\u002Fzenodo.org\u002Frecords\u002F12108189 | \n| 2024 | **Kolmogorov-Arnold Network (KAN) for Graphs** | - | - | [link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FKAN4Graph) |\n\n\n### Temporal Deep Graph Clustering\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting** | arxiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.19183) | - |\n| 2024 | **Deep Temporal Graph Clustering (TGC)** | ICLR | [Link](https:\u002F\u002Fopenreview.net\u002Fpdf?id=ViNe1fjGME) | [link](https:\u002F\u002Fgithub.com\u002FMGitHubL\u002FTGC) |\n\n### Deep Graph Clustering with Unknown Cluster Number\n\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **NeuroCUT: A Neural Approach for Robust Graph Partitioning** | KDD | [Link](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3637528.3671815) | [Link](https:\u002F\u002Fgithub.com\u002Fidea-iitd\u002FNeuroCut) |\n| 2024 | **LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering (LSEnet)** | ICML | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2405.11801) | [Link](https:\u002F\u002Fgithub.com\u002FZhenhHuang\u002FLSEnet\u002Ftree\u002Fmain) |\n| 2024 | **Masked AutoEncoder for Graph Clustering without Pre-defined Cluster Number k (GCMA)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2401.04741.pdf) | - |\n| 2023 | **Reinforcement Graph Clustering with Unknown Cluster Number (RGC)** | ACM MM | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.06827) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FRGC) \n\n\n\n\n\n### Reconstructive Deep Graph Clustering\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **Synergistic Deep Graph Clustering Network (SynC)** | Arxiv | [link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2406.15797) | [link](https:\u002F\u002Fgithub.com\u002FMarigoldwu\u002FSynC) | \n| 2024 | **Deep Masked Graph Node Clustering （DMGC）** | TCSS | [link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10550181) | - |\n| 2024 | **Multi-scale graph clustering network (MGCN)** | IS | [link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS002002552400937X) | [link](https:\u002F\u002Fgithub.com\u002FZj202309\u002FMGCN) | \n| 2024 | **An End-to-End Deep Graph Clustering via Online Mutual Learning** | TNNLS | [link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10412657) | - |\n| 2024 | **Contrastive Deep Nonnegative Matrix Factorization for Community Detection (CDNMF)** | ICASSP | [link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.02357) | [link](https:\u002F\u002Fgithub.com\u002F6lyc\u002FCDNMF) |\n| 2023 | **EGRC-Net: Embedding-Induced Graph Refinement Clustering Network (EGRC-Net)** | TIP | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=10326461) | [Link](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FTIP23---EGRC-Net) |\n| 2023 | **Beyond The Evidence Lower Bound: Dual Variational Graph Auto-Encoders For Node Clustering (BELBO-VGAE)** | SDM | [Link](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fpdf\u002F10.1137\u002F1.9781611977653.ch12) | [Link](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FBELBO-VGAE) |\n| 2023 | **Graph Clustering with Graph Neural Networks (DMoN)** | JMLR | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.16904) | [Link](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002Fgraph_embedding\u002Fdmon) |\n| 2023 | **Graph Clustering Network with Structure Embedding Enhanced (GC-SEE)** | PR | [link](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2023.109833) | [link](https:\u002F\u002Fgithub.com\u002FMarigoldwu\u002FGC-SEE) |\n| 2023 | **Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering (DGCN)** | ICML | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.02931) | [Link](https:\u002F\u002Fgithub.com\u002FPanern\u002FDGCN) |\n| 2023 | **Toward Convex Manifolds: A Geometric Perspective for Deep Graph Clustering of Single-cell RNA-seq Data (scTCM)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F0540.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FMMAMAR\u002FscTConvexMan) |\n| 2023 | **Exploring the Interaction between Local and Global Latent Configurations for Clustering Single-cell RNA-seq: A Unified Perspective (scTPF)** | AAAI | [Link](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26107) | [Link](https:\u002F\u002Fgithub.com\u002FMMAMAR\u002FscTPF) |\n| 2022 | **Escaping Feature Twist: A Variational Graph Auto-Encoder for Node Clustering (FT-VGAE)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2022\u002F465) | [Link](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FFT-VGAE) |\n| 2022 | **Deep Attention-guided Graph Clustering with Dual Self-supervision (DAGC)** | TCSVT | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=9999681) | [Link](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FDAGC) |\n| 2022 | **Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering (R-GAE)** | TKDE | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2107.08562) | [Link](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FR-GAE) |\n| 2022 | **Graph embedding clustering: Graph attention auto-encoder with cluster-specificity distribution (GEC-CSD)** | NN | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0893608021002008) | - |\n| 2022 | **Exploring temporal community structure via network embedding (VGRGMM)** | TCYB | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9768181) | - |\n| 2022 | **Cluster-Aware Heterogeneous Information Network Embedding (VaCA-HINE)** | WSDM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498385) | - |\n| 2022 | **Efficient Graph Convolution for Joint Node Representation Learning and Clustering (GCC)** | WSDM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3488560.3498533) | [Link](https:\u002F\u002Fgithub.com\u002Fchakib401\u002Fgraph_convolutional_clustering) |\n| 2022 | **ZINB-based Graph Embedding Autoencoder for Single-cell RNA-seq Interpretations (scTAG)** | AAAI | [Link](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-5060.YuZ.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FPhilyzh8\u002FscTAG) |\n| 2022 | **Graph community infomax(GCI)** | TKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3480244) | - |\n| 2022 | **Deep graph clustering with multi-level subspace fusion (DGCSF)** | PR | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS003132032200557X) | - |\n| 2022 | **Graph Clustering via Variational Graph Embedding (GC-VAE)** | PR | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0031320321005148) | - |\n| 2022 | **Deep neighbor-aware embedding for node clustering in attributed graphs (DNENC)** | PR | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0031320321004118) | - |\n| 2022 | **Collaborative Decision-Reinforced Self-Supervision for Attributed Graph Clustering (CDRS)** | TNNLS | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9777842) | [Link](https:\u002F\u002Fgithub.com\u002FJillian555\u002FTNNLS_CDRS) |\n| 2022 | **Embedding Graph Auto-Encoder for Graph Clustering (EGAE)** | TNNLS | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9741755) | [Link](https:\u002F\u002Fgithub.com\u002Fhyzhang98\u002FEGAE) |\n| 2021 | **Self-Supervised Graph Convolutional Network for Multi-View Clustering (SGCMC)** | TMM | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9472979\u002F) | [Link](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FSGCMC) |\n| 2021 | **Adaptive Hypergraph Auto-Encoder for Relational Data Clustering (AHGAE)** | TKDE | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fiel7\u002F69\u002F4358933\u002F09525190.pdf%3Fcasa_token%3DmbL8SLkmu8AAAAAA:mNPoE2n3BwaMZsYdRotHwa8Qs3uyzY53ZPVd0ixXutwqovM4vA7OSmsYWN3qXOAGW3CgH-LugHo&hl=en&sa=T&oi=ucasa&ct=ucasa&ei=_dvpYcTXCcCVy9YPgta4-AM&scisig=AAGBfm2V50SkaPV0K8x2F_mYsC15x028wA) | - | \n| 2021 | **Attention-driven Graph Clustering Network (AGCN)** | ACM MM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3474085.3475276?casa_token=P8cfxVYUtDYAAAAA:J3wHvLHJKu18558Us6rUHjgxXztBqOYMeNNuqFesIflTJiOefWkz8k2xnNzxJYfDYUyUP8BkUrazKA) | [Link](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FMM21---AGCN) |\n| 2021 | **Deep Fusion Clustering Network (DFCN)** | AAAI | [Link](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17198\u002F17005) | [Link](https:\u002F\u002Fgithub.com\u002FWxTu\u002FDFCN) |\n| 2020 | **Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning (CGCN)** | AAAI | [Link](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fdownload\u002F5843\u002F5699) | [Link](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FR-GAE\u002Ftree\u002Fmaster\u002FGMM-VGAE) |\n| 2020 | **Deep multi-graph clustering via attentive cross-graph association (DMGC)** | WSDM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3336191.3371806) | [Link](https:\u002F\u002Fgithub.com\u002Fflyingdoog\u002FDMGC) |\n| 2020 | **Going Deep: Graph Convolutional Ladder-Shape Networks (GCLN)** | AAAI | [Link](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5673\u002F5529) | - |\n| 2020 | **Multi-view attribute graph convolution networks for clustering (MAGCN)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0411.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FIMKBLE\u002FMAGCN) |\n| 2020 | **One2Multi Graph Autoencoder for Multi-view Graph Clustering (O2MAC)** | WWW | [Link](http:\u002F\u002Fshichuan.org\u002Fdoc\u002F83.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fgooglebaba\u002FWWW2020-O2MAC) |\n| 2020 | **Structural Deep Clustering Network (SDCN\u002FSDCN_Q)** | WWW | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.01633) | [Link](https:\u002F\u002Fgithub.com\u002Fbdy9527\u002FSDCN) |\n| 2020 | **Dirichlet Graph Variational Autoencoder (DGVAE)** | NeurIPS | [Link](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Ffile\u002F38a77aa456fc813af07bb428f2363c8d-Paper.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fxiyou3368\u002FDGVAE) |\n| 2019 | **RWR-GAE: Random Walk Regularization for Graph Auto Encoders (RWR-GAE)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.04003) | [Link](https:\u002F\u002Fgithub.com\u002FMysteryVaibhav\u002FRWR-GAE) |\n| 2019 | **Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning (GALA)** | ICCV | [Link](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fpapers\u002FPark_Symmetric_Graph_Convolutional_Autoencoder_for_Unsupervised_Graph_Representation_Learning_ICCV_2019_paper.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fsseung0703\u002FGALA_TF2.0) |\n| 2019 | **Attributed Graph Clustering: A Deep Attentional Embedding Approach (DAEGC)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0509.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FTiger101010\u002FDAEGC) |\n| 2019 | **Network-Specific Variational Auto-Encoder for Embedding in Attribute Networks (NetVAE)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F370) | - |\n| 2017 | **Graph Clustering with Dynamic Embedding (GRACE)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.08249) | [Link](https:\u002F\u002Fgithub.com\u002Fyangji9181\u002FGRACE?utm_source=catalyzex.com) | \n| 2017 | **MGAE: Marginalized Graph Autoencoder for Graph Clustering (MGAE)** | CIKM | [Link](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FShirui-Pan-3\u002Fpublication\u002F320882195_MGAE_Marginalized_Graph_Autoencoder_for_Graph_Clustering\u002Flinks\u002F5b76157b45851546c90a3d74\u002FMGAE-Marginalized-Graph-Autoencoder-for-Graph-Clustering.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FMGAE) |\n| 2017 | **Learning Community Embedding with Community Detection and Node Embedding on Graphs (ComE)** | CIKM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3132847.3132925?casa_token=R5eF-os9QxQAAAAA:GFW1TYwX8Yfs7ytT7tiVsAbNDJZhy0ZAVxzx3vYNBlKuwUKthV6OUuF0SdaKSX1DUMXVtr61SlJg0Q) | [Link](https:\u002F\u002Fgithub.com\u002Fvwz\u002FComE) |\n| 2016 | **Deep Neural Networks for Learning Graph Representations (DNGR)** | AAAI | [Link](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fdownload\u002F10179\u002F10038) | [Link](https:\u002F\u002Fgithub.com\u002FShelsonCao\u002FDNGR) |\n| 2015 | **Heterogeneous Network Embedding via Deep Architectures (HNE)** | SIGKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F2783258.2783296?casa_token=HCfko1SoHs0AAAAA:e5B7ZeoGp2DcuT5kj8KwnghRnMyQhoGhWhDEQoSCI6CkuhtIGshlvZzjLQT2c0LHO8R2jo_4KkVOuQ) | - |\n| 2014 | **Learning Deep Representations for Graph Clustering (GraphEncoder)** | AAAI | [Link](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F8916\u002F8775) | [Link](https:\u002F\u002Fgithub.com\u002Fquinngroup\u002Fdeep-representations-clustering) |\n\n\n\n\n\n\n\n### Adversarial Deep Graph Clustering\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :----: | :--------------------------------------------------------: | :--------------------------------------------: |\n| 2023 | **Wasserstein Adversarially Regularized Graph Autoencoder (WARGA)** | Neurocomputing | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2111.04981) | [Link](https:\u002F\u002Fgithub.com\u002FLeonResearch\u002FWARGA) |\n| 2022 | **Unsupervised network embedding beyond homophily (SELENE)** | TMLR | [Link](https:\u002F\u002Forbilu.uni.lu\u002Fbitstream\u002F10993\u002F53475\u002F1\u002FTMLR22b.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fzhiqiangzhongddu\u002FSELENE) |\n| 2020 | **JANE: Jointly adversarial network embedding (JANE)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0192.pdf) | - |\n| 2019 | **Adversarial Graph Embedding for Ensemble Clustering (AGAE)** | IJCAI | [Link](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10113653) | - |\n| 2019 | **CommunityGAN: Community Detection with Generative Adversarial Nets (CommunityGAN)** | WWW | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3308558.3313564) | [Link](https:\u002F\u002Fgithub.com\u002FSamJia\u002FCommunityGAN) |\n| 2019 | **ProGAN: Network embedding via proximity generative adversarial network (ProGAN)** | SIGKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3292500.3330866) | - |\n| 2019 | **Learning Graph Embedding with Adversarial Training Methods (ARGA\u002FARVGA)** | TCYB | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.01250) | [Link](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FARGA) |\n| 2019 | **Adversarially Regularized Graph Autoencoder for Graph Embedding (ARGA\u002FARVGA)** | IJCAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.04407) | [Link](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FARGA) |\n\n\n\n\n### Contrastive Deep Graph Clustering\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective** | SIGKDD | [link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2406.14288) | [link](https:\u002F\u002Fgithub.com\u002FEdisonLeeeee\u002FMAGI?tab=readme-ov-file) |\n| 2024 | **GLAC-GCN: Global and Local Topology-Aware Contrastive Graph Clustering Network (GLAC-GCN)** | TAI | [link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10557452) | [link](https:\u002F\u002Fgithub.com\u002Fxuyuankun631\u002FGLAC-GCN) |\n| 2024 | **Contrastive Multiview Attribute Graph Clustering With Adaptive Encoders** | TNNLS | [link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10509800) | - |\n| 2024 | **Contrastive Deep Nonnegative Matrix Factorization for Community Detection (CDNMF)** | ICASSP | [link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.02357) | [link](https:\u002F\u002Fgithub.com\u002F6lyc\u002FCDNMF) |\n| 2023 | **A Contrastive Variational Graph Auto-Encoder for Node Clustering (CVGAE)** | PR | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0031320323009068) | [Link](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FCVGAE_PR) | \n| 2023 | **Dual Contrastive Learning Network for Graph Clustering** | TNNLS | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10097557) | [Link](https:\u002F\u002Fgithub.com\u002FXinPeng97\u002FTNNLS_DCLN) | \n| 2023 | **Contrastive Learning with Cluster-Preserving Augmentation for Attributed Graph Clustering** | ECML-PKDD | [Link](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-031-43412-9_38) | - | \n| 2023 | **Graph Contrastive Representation Learning with Input-Aware and Cluster-Aware Regularization** | ECML-PKDD | [Link](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-031-43415-0_39) | - |\n| 2023 | **Reinforcement Graph Clustering with Unknown Cluster Number (RGC)** | ACM MM | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.06827) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FRGC) \n| 2023 | **Self-Contrastive Graph Diffusion Network** | ACM MM | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2307.14613.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fkunzhan\u002FSCDGN) \n| 2023 | **CONVERT: Contrastive Graph Clustering with Reliable Augmentation (CONVERT)** | ACM MM | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.08963.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fxihongyang1999\u002FCONVERT) |\n| 2023 | **Attribute Graph Clustering via Learnable Augmentation (AGCLA)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2212.03559.pdf) | - |\n| 2023 | **CARL-G: Clustering-Accelerated Representation Learning on Graphs (CARL-G)** | SIGKDD | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2306.06936.pdf) | - |\n| 2023 | **Dink-Net: Neural Clustering on Large Graphs (Dink-Net)** | ICML | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.18405.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FDink-Net) |\n| 2023 | **CONGREGATE: Contrastive Graph Clustering in Curvature Spaces (CONGREGATE)**| IJCAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.03555.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FCurvCluster\u002FCongregate) |\n| 2023 | **Multi-level Graph Contrastive Prototypical Clustering**| IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F0513.pdf) | - | \n| 2023 | **Simple Contrastive Graph Clustering (SCGC)** | TNNLS | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.07865) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FSCGC) |\n| 2023 | **Hard Sample Aware Network for Contrastive Deep Graph Clustering (HSAN)** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.08665) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FHSAN) |\n| 2023 | **Cluster-guided Contrastive Graph Clustering Network (CCGC)** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.01098) | [Link](https:\u002F\u002Fgithub.com\u002Fxihongyang1999\u002FCCGC) |\n| 2022 | **NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering (NCAGC)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.07897) | [Link](https:\u002F\u002Fgithub.com\u002Fwangtong627\u002FDual-Contrastive-Attributed-Graph-Clustering-Network) |\n| 2022 | **SCGC : Self-Supervised Contrastive Graph Clustering (SCGC)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2204.12656) | [Link](https:\u002F\u002Fgithub.com\u002Fgayanku\u002FSCGC) |\n| 2022 | **Improved Dual Correlation Reduction Network (IDCRN)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.12533) | - |\n| 2022 | **Towards Self-supervised Learning on Graphs with Heterophily (HGRL)** | CIKM | [Link](https:\u002F\u002Fscholar.archive.org\u002Fwork\u002Fchm4lsfonvbfree7n36vqlcl4a\u002Faccess\u002Fwayback\u002Fhttps:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3511808.3557478) | [Link](https:\u002F\u002Fgithub.com\u002FyifanQi98\u002FHGRL) |\n| 2022 | **S3GC: Scalable Self-Supervised Graph Clustering (S3GC)** | NeurIPS | [Link](https:\u002F\u002Fopenreview.net\u002Fforum?id=ldl2V3vLZ5) | [Link](https:\u002F\u002Fgithub.com\u002Fdevvrit\u002FS3GC) |\n| 2022 | **Self-consistent Contrastive Attributed Graph Clustering with Pseudo-label Prompt (SCAGC)** | TMM | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.08264) | [Link](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FSCAGC) |\n| 2022 | **CGC: Contrastive Graph Clustering for Community Detection and Tracking (CGC)** | WWW | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.08504) | - |\n| 2022 | **Towards Unsupervised Deep Graph Structure Learning (SUBLIME)** | WWW | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2201.06367.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FSUBLIME) |\n| 2022 | **Attributed Graph Clustering with Dual Redundancy Reduction (AGC-DRR)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2022\u002F0418.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fgongleii\u002FAGC-DRR) |\n| 2022 | **Deep Graph Clustering via Dual Correlation Reduction (DCRN)** | AAAI | [Link](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-5928.LiuY.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FDCRN) |\n| 2022 | **RepBin: Constraint-Based Graph Representation Learning for Metagenomic Binning (RepBin)** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2112.11696.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fxuehansheng\u002FRepBin) |\n| 2022 | **Augmentation-Free Self-Supervised Learning on Graphs (AFGRL)** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2112.02472) | [Link](https:\u002F\u002Fgithub.com\u002FNamkyeong\u002FAFGRL) |\n| 2022 | **SAIL: Self-Augmented Graph Contrastive Learning (SAIL)** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.00934) | - |\n| 2021 | **Graph Debiased Contrastive Learning with Joint Representation Clustering (GDCL)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0473.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fhzhao98\u002FGDCL) |\n| 2021 | **Multi-view Contrastive Graph Clustering (MCGC)** | NeurIPS | [Link](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2021\u002Ffile\u002F10c66082c124f8afe3df4886f5e516e0-Paper.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fpanern\u002Fmcgc) |\n| 2021 | **Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning (HeCo)** | SIGKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467415) | [Link](https:\u002F\u002Fgithub.com\u002Fliun-online\u002FHeCo) |\n| 2020 | **Adaptive Graph Encoder for Attributed Graph Embedding (AGE)** | SIGKDD | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.01594) | [Link](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FAGE) |\n| 2020 | **CommDGI: Community Detection Oriented Deep Graph Infomax (CommDGI)** | CIKM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412042) | [Link](https:\u002F\u002Fgithub.com\u002FFDUDSDE\u002FCommDGI) |\n| 2020 | **Contrastive Multi-View Representation Learning on Graphs (MVGRL)** | ICML | [Link](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fhassani20a\u002Fhassani20a.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fkavehhassani\u002Fmvgrl) |\n\n\n### Application\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :---------: | :----------------------------------------------------------: | :--: |\n| 2024 | **EyeGraph: Modularity-aware Spatio Temporal Graph Clustering for Continuous Event-based Eye Tracking** | NeurIPS | [Link](https:\u002F\u002Fink.library.smu.edu.sg\u002Fcgi\u002Fviewcontent.cgi?params=\u002Fcontext\u002Fsis_research\u002Farticle\u002F10909\u002F&path_info=2367_EyeGraph_Modularity_aware.pdf) | - | \n| 2024 | **Identify Then Recommend: Towards Unsupervised Group Recommendation (ITR)** | NeurIPS | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.23757) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FITR) | \n| 2024 | **End-to-end Learnable Clustering for Intent Learning in Recommendation (ELCRec)** | NeurIPS | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2401.05975.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FELCRec) | \n| 2023 | **GuardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering** | TIFS | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F11275861) | [Link](https:\u002F\u002Fgithub.com\u002Fcsyuhao\u002FGuardFL-Official) |\n\n\n### Others\n\n\n| Year | Title | Venue | Paper | Code |\n| ---- | ------------------------------------------------------------ | :----: | :--------------------------------------------------------: | :--------------------------------------------: |\n| 2023 | **Robust Graph Clustering via Meta Learning for Noisy Graphs (MetaGC)** | CIKM | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.00322) | [Link](https:\u002F\u002Fgithub.com\u002FHyeonsooJo\u002FMetaGC) |\n\n\n\n## Other Related Papers\n\n### Deep Clustering\n\n| Year | Title | **Venue** | Paper | Code |\n| :--: | :----------------------------------------------------------- | :-------: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **ProCom: A Few-shot Targeted Community Detection Algorithm** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2408.07369) | [Link](https:\u002F\u002Fgithub.com\u002FWxxShirley\u002FKDD2024ProCom?tab=readme-ov-file) | \n| 2024 | **Deep graph clustering by integrating community structure with neighborhood information (DIGC)** | IS | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS002002552400865X) | - |\n| 2024 | **Information-enhanced deep graph clustering network (IEDGCN)** | Neurocomputing | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092523122400763X) | - |\n| 2024 | **Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2401.06595v1) | [Link](https:\u002F\u002Fgithub.com\u002Fq086\u002FDyFSS) | \n| 2024 | **DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (DGCluster)** | AAAI | [Link](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28983) | - |\n| 2023 | **Mutual Boost Network for attributed graph clustering (MBN)**| KBS | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417423009818) | - |\n| 2023 | **Redundancy-Free Self-Supervised Relational Learning for Graph Clustering**| TNNLS | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2309.04694.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fyisiyu95\u002FR2FGC) |\n| 2023 | **Spectral Clustering of Attributed Multi-relational Graphs**| SIGKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3447548.3467381) | - |\n| 2023 | **Local Graph Clustering with Noisy Labels**| Arxiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2310.08031.pdf) | - |\n| 2023 | **A Re-evaluation of Deep Learning Methods for Attributed Graph Clustering**| CIKM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3583780.3614768) | [Link](https:\u002F\u002Fgithub.com\u002F2100271064\u002FA-Re-evaluation-of-Deep-Learning-Methods-for-Attributed-Graph-Clustering) |\n| 2023 | **Robust Graph Clustering via Meta Weighting for Noisy Graphs**| CIKM | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2311.00322.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FHyeonsooJo\u002FMetaGC) |\n| 2023 | **Homophily-enhanced Structure Learning for Graph Clustering**| CIKM | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.05309.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fgalogm\u002FHoLe) |\n| 2023 | **A Re-evaluation of Deep Learning Methodsfor Attributed Graph Clustering** | CIKM | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3583780.3614768) | [Link](https:\u002F\u002Fgithub.com\u002F2100271064\u002FA-Re-evaluation-of-Deep-Learning-Methods-for-Attributed-Graph-Clustering) |\n| 2023 | **Beyond The Evidence Lower Bound: Dual Variational Graph Auto-Encoders For Node Clustering** | SDM | [Link](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977653.ch12) | [Link](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FBELBO-VGAE) |\n| 2023 | **GC-Flow: A Graph-Based Flow Network for Effective Clustering** | ICLM | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.17284.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fxztcwang\u002FGCFlow) |\n| 2023 | **Scalable Attributed-Graph Subspace Clustering (SAGSC)** | AAAI | [Link](https:\u002F\u002Fchakib401.github.io\u002Ffiles\u002FSAGSC.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fchakib401\u002Fsagsc) |\n| 2022 | **Adaptive Attribute and Structure Subspace Clustering Network (AASSC-Net)** | TIP | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fiel7\u002F83\u002F9626658\u002F09769915.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FTIP22---AASSC-Net) |\n| 2022 | **Twin Contrastive Learning for Online Clustering** | IJCV | [Link](http:\u002F\u002Fpengxi.me\u002Fwp-content\u002Fuploads\u002F2022\u002F07\u002FTwin-Contrastive-Learning-for-Online-Clustering.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FYunfan-Li\u002FTwin-Contrastive-Learning) |\n| 2022 | **Non-Graph Data Clustering via O(n) Bipartite Graph Convolution** | TPAMI | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9996549) | [Link](https:\u002F\u002Fgithub.com\u002Fhyzhang98\u002FAnchorGAE-torch) |\n| 2022 | **Ada-nets: Face clustering via adaptive neighbor discovery in the structure space** | ICLR | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.03800) | [Link](https:\u002F\u002Fgithub.com\u002Fdamo-cv\u002FAda-NETS) |\n| 2021 | **Adaptive Graph Auto-Encoder for General Data Clustering** | TPAMI | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9606581) | [Link](https:\u002F\u002Fgithub.com\u002Fhyzhang98\u002FAdaGAE) |\n| 2021 | **Contrastive Clustering** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.09687.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FYunfan-Li\u002FContrastive-Clustering) |\n| 2017 | **Towards k-means-friendly spaces: Simultaneous deep learning and clustering (DCN)** | ICML | [Link](http:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Fyang17b\u002Fyang17b.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fboyangumn\u002FDCN) |\n| 2017 | **Improved Deep Embedded Clustering with Local Structure Preservation (IDEC)** | IJCAI | [Link](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FXifeng-Guo\u002Fpublication\u002F317095655_Improved_Deep_Embedded_Clustering_with_Local_Structure_Preservation\u002Flinks\u002F59263224458515e3d4537edc\u002FImproved-Deep-Embedded-Clustering-with-Local-Structure-Preservation.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FXifengGuo\u002FIDEC) |\n| 2016 | **Unsupervised Deep Embedding for Clustering Analysis (DEC)** | ICML | [Link](http:\u002F\u002Fproceedings.mlr.press\u002Fv48\u002Fxieb16.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fpiiswrong\u002Fdec) |\n\n\n\n### Deep Hierarchical Clustering\n\n| Year | Title | **Venue** | Paper | Code |\n| :--: | :----------------------------------------------------------- | :-------: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2023 | **Contrastive Hierarchical Clustering (CHC)**| ECML PKDD | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.03389) | [Link](https:\u002F\u002Fgithub.com\u002FMichalZnalezniak\u002FContrastive-Hierarchical-Clustering) |\n\n\n\n### Other Related Methods\n\n| Year | Title | **Venue** | Paper | Code |\n| :--: | :----------------------------------------------------------- | :-------: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **PSMC: Provable and Scalable Algorithms for Motif Conductance Based Graph Clustering**|KDD | [Link](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3637528.3671666) | - |\n| 2024 | **Effective Clustering on Large Attributed Bipartite Graphs (TPO)** | arXiv | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3637528.3671764) | - |\n| 2023 | **GPUSCAN++: Efficient Structural Graph Clustering on GPUs** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2311.12281.pdf) | - |\n| 2022 | **Deep linear graph attention model for attributed graph clustering** | Knowl Based Syst | [Link](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.108665) | - |\n| 2022 | **Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning** | WWW | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2112.15530) | - |\n| 2022 | **X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning (X-GOAL)** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.03560) | - |\n| 2022 | **Deep Graph Clustering with Multi-Level Subspace Fusion** | PR | [Link](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2022.109077) |-|\n| 2022 | **GRACE: A General Graph Convolution Framework for Attributed Graph Clustering** | TKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3544977) | [Link](https:\u002F\u002Fgithub.com\u002FBarakeelFanseu\u002FGRACE) | |\n| 2022 | **Fine-grained Attributed Graph Clustering** | SDM | [Link](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977172.42) | [Link](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FFGC) |\n| 2022 | **Multi-view graph embedding clustering network: Joint self-supervision and block diagonal representation** | NN | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS089360802100397X?via%3Dihub) | [Link](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FNN-2022-MVGC) |\n| 2022 | **SAGES: Scalable Attributed Graph Embedding with Sampling for Unsupervised Learning** | TKDE | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9705119) | - |\n| 2022 | **Automated Self-Supervised Learning For Graphs** | ICLR | [Link](https:\u002F\u002Fopenreview.net\u002Fforum?id=rFbR4Fv-D6-) | [Link](https:\u002F\u002Fgithub.com\u002FChandlerBang\u002FAutoSSL) |\n| 2022 | **Stationary diffusion state neural estimation for multi-view clustering** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.01334) | [Link](https:\u002F\u002Fgithub.com\u002Fkunzhan\u002FSDSNE) |\n| 2021 | **Simple Spectral Graph Convolution** | ICLR | [Link](https:\u002F\u002Fopenreview.net\u002Fpdf?id=CYO5T-YjWZV) | [Link](https:\u002F\u002Fgithub.com\u002Fallenhaozhu\u002FSSGC) |\n| 2021 | **Spectral embedding network for attributed graph clustering (SENet)** | NN | [Link](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0893608021002227) | - |\n| 2021 | **Smoothness Sensor: Adaptive Smoothness Transition Graph Convolutions for Attributed Graph Clustering** | TCYB | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9514513) | [Link](https:\u002F\u002Fgithub.com\u002FaI-area\u002FNASGC) |\n| 2021 | **Multi-view Attributed Graph Clustering** | TKDE | [Link](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FZhao-Kang-6\u002Fpublication\u002F353747180_Multi-view_Attributed_Graph_Clustering\u002Flinks\u002F612059cd0c2bfa282a5cd55e\u002FMulti-view-Attributed-Graph-Clustering.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FMAGC) |\n| 2021 | **High-order Deep Multiplex Infomax** | WWW | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07810) | [Link](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FHDMI) |\n| 2021 | **Graph InfoClust: Maximizing Coarse-Grain Mutual Information in Graphs** | PAKDD | [Link](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-030-75762-5_43) | [Link](https:\u002F\u002Fgithub.com\u002Fcmavro\u002FGraph-InfoClust-GIC) |\n| 2021 | **Graph Filter-based Multi-view Attributed Graph Clustering** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0375.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FMvAGC) |\n| 2021 | **Graph-MVP: Multi-View Prototypical Contrastive Learning for Multiplex Graphs** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.03560) | [Link](https:\u002F\u002Fgithub.com\u002Fchao1224\u002FGraphMVP) |\n| 2021 | **Contrastive Laplacian Eigenmaps** | NeurIPS | [Link](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002F2d1b2a5ff364606ff041650887723470-Paper.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fallenhaozhu\u002FCOLES) |\n| 2020 | **Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning** | arXiv | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01674) | - |\n| 2020 | **Distribution-induced Bidirectional GAN for Graph Representation Learning** | CVPR | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1912.01899) | [Link](https:\u002F\u002Fgithub.com\u002FSsGood\u002FDBGAN) |\n| 2020 | **Adaptive Graph Converlutional Network with Attention Graph Clustering for Co saliency Detection** | CVPR | [Link](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2020\u002Fpapers\u002FZhang_Adaptive_Graph_Convolutional_Network_With_Attention_Graph_Clustering_for_Co-Saliency_CVPR_2020_paper.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fltp1995\u002FGCAGC-CVPR2020) |\n| 2020 | **Spectral Clustering with Graph Neural Networks for Graph Pooling (MinCutPool)** | ICML | [Link](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fbianchi20a\u002Fbianchi20a.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FFilippoMB\u002FSpectral-Clustering-with-Graph-Neural-Networks-for-Graph-Pooling) |\n| 2020 | **MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding** | WWW | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.01680) | [Link](https:\u002F\u002Fgithub.com\u002Fcynricfu\u002FMAGNN) |\n| 2020 | **Unsupervised Attributed Multiplex Network Embedding** | AAAI | [Link](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.06750) | [Link](https:\u002F\u002Fgithub.com\u002Fpcy1302\u002FDMGI) |\n| 2020 | **Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure** | ICDM | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9338269) | [Link](https:\u002F\u002Fgithub.com\u002FFakeTibbers\u002FCross-Graph) |\n| 2020 | **Multi-class imbalanced graph convolutional network learning** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0398.pdf) | - |\n| 2020 | **CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning** | arXiv | [Link](http:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01674) | - |\n| 2020 | **Attributed Graph Clustering via Deep Adaptive Graph Maximization** | ICCKE | [Link](https:\u002F\u002Fieeexplore-ieee-org-s.nudtproxy.yitlink.com\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9303694) | - |\n| 2019 | **Heterogeneous Graph Attention Network (HAN)** | WWW | [Link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.07293.pdf) | [Link](https:\u002F\u002Fgithub.com\u002FJhy1993\u002FHAN) |\n| 2019 | **Multi-view Consensus Graph Clustering** | TIP | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8501973) | [Link](https:\u002F\u002Fgithub.com\u002Fkunzhan\u002FMCGC) |\n| 2019 | **Attributed Graph Clustering via Adaptive Graph Convolution (AGC)** | IJCAI | [Link](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0601.pdf) | [Link](https:\u002F\u002Fgithub.com\u002Fkarenlatong\u002FAGC-master) |\n| 2016 | **node2vec: Scalable Feature Learning for Networks (node2vec)** | SIGKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F2939672.2939754?casa_token=jt4dhGo-tKEAAAAA:lhscLc-u0XZFYYyi48kXK3_vtYR-PffsbbMRZdtpbaprcB1FGyjWH1RvstHACYALyZ9OtUf2nv_FjQ) | [Link](http:\u002F\u002Fsnap.stanford.edu\u002Fnode2vec\u002F) |\n| 2016 | **Variational Graph Auto-Encoders (GAE)** | NeurIPS Workshop | [Link](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9046288) | [Link](https:\u002F\u002Fgithub.com\u002Ftkipf\u002Fgae) |\n| 2015 | **LINE: Large-scale Information Network Embedding (LINE)** | WWW | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F2736277.2741093?casa_token=ahQ9yUhknkAAAAAA:lP6rusbODmZ1ZpGxF-cIiiopMiAA8Q4I02cBBbfE5dc8-NQpiPOdV0cv4-43lA9CkTXU4mPei39UDg) | [Link](https:\u002F\u002Fgithub.com\u002Ftangjianpku\u002FLINE) |\n| 2014 | **DeepWalk: Online Learning of Social Representations (DeepWalk)** | SIGKDD | [Link](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F2623330.2623732?casa_token=x6Gui_HExYoAAAAA:mzfm0BH0rSX7qcQV2WJ6uTSsg7zjnPalmOQ8sQuoJrwXfh9fcDgVPgXb-APCLGk1qWsPpIkBhI61pw) | [Link](https:\u002F\u002Fgithub.com\u002Fphanein\u002Fdeepwalk) |\n\n\n\n\n## Benchmark Datasets\n\nWe divide the datasets into two categories, i.e. graph datasets and non-graph datasets. Graph datasets are some graphs in real-world, such as citation networks, social networks and so on. Non-graph datasets are NOT graph type. However, if necessary, we could construct \"adjacency matrices\" by K-Nearest Neighbors (KNN) algorithm.\n\n\n\n#### Quick Start\n\n- Step1: Download all datasets from \\[[Google Drive](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1thSxtAexbvOyjx-bJre8D4OyFKsBe1bK?usp=sharing) | [Nutstore](https:\u002F\u002Fwww.jianguoyun.com\u002Fp\u002FDfzK1pwQwdaSChjI2aME)]. Optionally, download some of them from URLs in the tables (Google Drive)\n- Step2: Unzip them to **.\u002Fdataset\u002F**\n- Step3: Change the type and the name of the dataset in **main.py**\n- Step4: Run the **main.py**\n\n\n\n#### Code\n\n- **utils.py**\n 1. **load_graph_data**: load graph datasets \n 2. **load_data**: load non-graph datasets\n 3. **normalize_adj**: normalize the adjacency matrix\n 4. **diffusion_adj**: calculate the graph diffusion\n 5. **construct_graph**: construct the knn graph for non-graph datasets\n 6. **numpy_to_torch**: convert numpy to torch\n 7. **torch_to_numpy**: convert torch to numpy\n- **clustering.py**\n 1. **setup_seed**: fix the random seed\n 2. **evaluation**: evaluate the performance of clustering\n 3. **k_means**: K-means algorithm\n- **visualization.py**\n 1. **t_sne**: t-SNE algorithm\n 2. **similarity_plot**: visualize cosine similarity matrix of the embedding or feature\n\n\n\n#### Datasets Details\n\nAbout the introduction of each dataset, please check [here](.\u002Fdataset\u002FREADME.md)\n\n1. Graph Datasets\n\n | Dataset | # Samples | # Dimension | # Edges | # Classes | URL |\n | :------: | :-------: | :---------: | :-----: | :-------: | :----------------------------------------------------------: |\n | CORA | 2708 | 1433 | 5278 | 7 | [cora.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1_LesghFTQ02vKOBUfDP8fmDF1JP3MPrJ\u002Fview?usp=sharing) |\n | CITESEER | 3327 | 3703 | 4552 | 6 | [citeseer.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1dEsxq5z5dc35tS3E46pg6pc2LUMlF6jF\u002Fview?usp=sharing) |\n | CITE | 3327 | 3703 | 4552 | 6 | [cite.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1dEsxq5z5dc35tS3E46pg6pc2LUMlF6jF\u002Fview?usp=sharing) |\n | PUBMED | 19717 | 500 | 44324 | 3 | [pubmed.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1tdr20dvvjZ9tBHXj8xl6wjO9mQzD0rzA\u002Fview?usp=sharing) |\n | DBLP | 4057 | 334 | 3528 | 4 | [dblp.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1XWWMIDyvCQ4VJFnAmXS848ksN9MFm5ys\u002Fview?usp=sharing) |\n | ACM | 3025 | 1870 | 13128 | 3 | [acm.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F19j7zmQ-AMgzTX7yZoKzUK5wVxQwO5alx\u002Fview?usp=sharing) |\n | AMAP | 7650 | 745 | 119081 | 8 | [amap.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1qqLWPnBOPkFktHfGMrY9nu8hioyVZV31\u002Fview?usp=sharing) |\n | AMAC | 13752 | 767 | 245861 | 10 | [amac.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1DJhSOYWXzlRDSTvaC27bSmacTbGq6Ink\u002Fview?usp=sharing) |\n | CORAFULL | 19793 | 8710 | 63421 | 70 | [corafull.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1XLqs084J3xgWW9jtbBXJOmmY84goT1CE\u002Fview?usp=sharing) |\n | WIKI | 2405 | 4973 | 8261 | 17 | [wiki.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1vxupFQaEvw933yUuWzzgQXxIMQ_46dva\u002Fview?usp=sharing) |\n | COCS | 18333 | 6805 | 81894 | 15 | [cocs.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F186twSfkDNmqh9L618iCeWq4DA7Lnpte0\u002Fview?usp=sharing) |\n | CORNELL | 183 | 1703 | 149 | 5 | [cornell.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1EjpHP26Oh0_qHl13vOfEzc4ZyzkGrR-M\u002Fview?usp=sharing) |\n | TEXAS | 183 | 1703 | 162 | 5 | [texas.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1kpz6b9-OsEU1RsAyxWWeUgzhdd3-koI2\u002Fview?usp=sharing) |\n | WISC | 251 | 1703 | 257 | 5 | [wisc.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1I8v1H1IthEiWd4IoV-wXNF6g1Wtg_sVC\u002Fview?usp=sharing) |\n | FILM | 7600 | 932 | 15009 | 5 | [film.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1s5K9Gb235-gO-IwevJLKAts7jExnnmrC\u002Fview?usp=sharing) |\n | BAT | 131 | 81 | 1038 | 4 | [bat.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1hRPtdFo9CzcxlFb84NWXg-HmViZnqshu\u002Fview?usp=sharing) |\n | EAT | 399 | 203 | 5994 | 4 | [eat.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1iE0AFKs1V5-nMk2XhV-TnfmPhvh0L9uo\u002Fview?usp=sharing) |\n | UAT | 1190 | 239 | 13599 | 4 | [uat.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1RUTHp54dVPB-VGPsEk8tV32DsSU0l-n_\u002Fview?usp=sharing) |\n \n\n**Edges**: Here, we just count the number of undirected edges.\n\n2. Non-graph Datasets\n\n | Dataset | Samples | Dimension | Type | Classes | URL |\n | :-----: | :-----: | :-------: | :----: | :-----: | :----------------------------------------------------------: |\n | USPS | 9298 | 256 | Image | 10 | [usps.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F19oBkSeIluW3A5kcV7W0UM1Bt6V9Q62e-\u002Fview?usp=sharing) |\n | HHAR | 10299 | 561 | Record | 6 | [hhar.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F126OFuNhf2u-g9Tr0wukk0T8uM1cuPzy2\u002Fview?usp=sharing) |\n | REUT | 10000 | 2000 | Text | 4 | [reut.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F12MpPWyN87bu-AQYTyjdEcofy1mgjgzi9\u002Fview?usp=sharing) |\n\n\n\n## Citation\n\n```\n\n@inproceedings{ITR,\n title={Identify Then Recommend: Towards Unsupervised Group Recommendation},\n author={Liu, Yue and Zhu, Shihao and Yang, Tianyuan and Ma, Jian and Zhong, Wenliang},\n booktitle={Proc. of NeurIPS},\n year={2024}\n}\n\n@article{ELCRec,\n title={End-to-end Learnable Clustering for Intent Learning in Recommendation},\n author={Liu, Yue and Zhu, Shihao and Xia, Jun and Ma, Yingwei and Ma, Jian and Zhong, Wenliang and Zhang, Guannan and Zhang, Kejun and Liu, Xinwang},\n booktitle={Proceedings of International Conference on Neural Information Processing Systems},\n year={2024}\n}\n\n@article{deep_graph_clustering_survey,\n title={A Survey of Deep Graph Clustering: Taxonomy, Challenge, and Application},\n author={Liu, Yue and Xia, Jun and Zhou, Sihang and Wang, Siwei and Guo, Xifeng and Yang, Xihong and Liang, Ke and Tu, Wenxuan and Li, Z. Stan and Liu, Xinwang},\n journal={arXiv preprint arXiv:2211.12875},\n year={2022}\n}\n\n@article{SCGC,\n title={Simple contrastive graph clustering},\n author={Liu, Yue and Yang, Xihong and Zhou, Sihang and Liu, Xinwang and Wang, Siwei and Liang, Ke and Tu, Wenxuan and Li, Liang},\n journal={IEEE Transactions on Neural Networks and Learning Systems},\n year={2023},\n publisher={IEEE}\n}\n\n@inproceedings{Dink_Net,\n title={Dink-net: Neural clustering on large graphs},\n author={Liu, Yue and Liang, Ke and Xia, Jun and Zhou, Sihang and Yang, Xihong and Liu, Xinwang and Li, Stan Z},\n booktitle={Proceedings of International Conference on Machine Learning},\n year={2023}\n}\n\n@inproceedings{TGC_ML_ICLR,\n title={Deep Temporal Graph Clustering},\n author={Liu, Meng and Liu, Yue and Liang, Ke and Tu, Wenxuan and Wang, Siwei and Zhou, Sihang and Liu, Xinwang},\n booktitle={The 12th International Conference on Learning Representations},\n year={2024}\n}\n\n@inproceedings{HSAN,\n title={Hard sample aware network for contrastive deep graph clustering},\n author={Liu, Yue and Yang, Xihong and Zhou, Sihang and Liu, Xinwang and Wang, Zhen and Liang, Ke and Tu, Wenxuan and Li, Liang and Duan, Jingcan and Chen, Cancan},\n booktitle={Proceedings of the AAAI conference on artificial intelligence},\n volume={37},\n number={7},\n pages={8914-8922},\n year={2023}\n}\n\n@inproceedings{DCRN,\n title={Deep Graph Clustering via Dual Correlation Reduction},\n author={Liu, Yue and Tu, Wenxuan and Zhou, Sihang and Liu, Xinwang and Song, Linxuan and Yang, Xihong and Zhu, En},\n booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},\n volume={36},\n number={7},\n pages={7603-7611},\n year={2022}\n}\n\n@inproceedings{liuyue_RGC,\n title={Reinforcement Graph Clustering with Unknown Cluster Number},\n author={Liu, Yue and Liang, Ke and Xia, Jun and Yang, Xihong and Zhou, Sihang and Liu, Meng and Liu, Xinwang and Li, Stan Z},\n booktitle={Proceedings of the 31st ACM International Conference on Multimedia},\n pages={3528--3537},\n year={2023}\n}\n\n@article{RGAE,\n title={Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering},\n author={Mrabah, Nairouz and Bouguessa, Mohamed and Touati, Mohamed Fawzi and Ksantini, Riadh},\n journal={IEEE Transactions on Knowledge and Data Engineering},\n year={2022}\n}\n\n@article{yu2025guard,\n title = {G${}^2$uardFL: Safeguarding Federated Learning against Backdoor Attacks via Attributed Client Graph Clustering},\n author = {Hao Yu and Chuan Ma and Meng Liu and Tianyu Du and Ming Ding and Tao Xiang and Shouling Ji and Xinwang Liu},\n journal = {IEEE Transactions on Information Forensics and Security},\n year = {2025},\n doi = {10.1109\u002FTIFS.2025.3639985}\n}\n```\n\n\n\n## Other Related Awesome Repository\n\n[A-Unified-Framework-for-Deep-Attribute-Graph-Clustering](https:\u002F\u002Fgithub.com\u002FMarigoldwu\u002FA-Unified-Framework-for-Deep-Attribute-Graph-Clustering)\n\n[Awesome-Deep-Group-Recommendation](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Group-Recommendation)\n\n[Awesome-Partial-Graph-Machine-Learning](https:\u002F\u002Fgithub.com\u002FWxTu\u002FAwesome-Partial-Graph-Machine-Learning)\n\n[Awesome-Knowledge-Graph-Reasoning](https:\u002F\u002Fgithub.com\u002FLIANGKE23\u002FAwesome-Knowledge-Graph-Reasoning)\n\n[Awesome-Temporal-Graph-Learning](https:\u002F\u002Fgithub.com\u002FMGitHubL\u002FAwesome-Temporal-Graph-Learning)\n\n[Awesome-Deep-Multiview-Clustering](https:\u002F\u002Fgithub.com\u002Fjinjiaqi1998\u002FAwesome-Deep-Multiview-Clustering)\n\n\n\n","[python-img]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flanguages\u002Ftop\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering?color=lightgrey\n[stars-img]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering?color=yellow\n[stars-url]: https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering\u002Fstargazers\n[fork-img]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering?color=lightblue&label=fork\n[fork-url]: https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering\u002Fnetwork\u002Fmembers\n[visitors-img]: https:\u002F\u002Fvisitor-badge.glitch.me\u002Fbadge?page_id=yueliu1999.Awesome-Deep-Graph-Clustering\n[adgc-url]: https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering\n\n# ADGC：超赞深度图聚类\n\nADGC 是一个汇集了最先进（SOTA）、新颖的深度图聚类方法（论文、代码和数据集）的资源库。欢迎提交其他有趣的论文和代码。如有任何问题，请联系 yueliu19990731@163.com。如果您觉得本仓库对您的研究或工作有所帮助，真诚地感谢您为本仓库点亮星标。:sparkles: 如果您在研究中使用了本仓库中的代码或处理后的数据集，请在引用部分 [此处](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering#citation) 引用 2–3 篇相关论文。:heart:\n\n[![由 Python 制作][python-img]][adgc-url]\n[![GitHub 星标数][stars-img]][stars-url]\n[![GitHub 分支数][fork-img]][fork-url]\n[![访问量][visitors-img]][adgc-url]\n\n--------------\n\n## 什么是深度图聚类？\n\n深度图聚类旨在揭示底层图结构，并将节点划分为不同的群组，近年来受到了广泛关注。更多细节请参阅综述论文。[链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.12875)\n\n\u003Cdiv align=\"center\"> \n \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyueliu1999_Awesome-Deep-Graph-Clustering_readme_feec4e5d784c.png\" width=90% \u002F>\n\u003C\u002Fdiv>\n\n\n\n## 重要综述论文\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :---------: | :----------------------------------------------------------: | :--: |\n| 2023 | **高级深度图节点聚类概述** | TCSS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10049408) | - |\n| 2022 | **深度图聚类综述：分类、挑战与应用** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.12875) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering) |\n| 2022 | **基于深度学习的社区发现综合综述** | TNNLS | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2105.12584.pdf?ref=https:\u002F\u002Fgithubhelp.com) | - |\n| 2020 | **图神经网络综合综述** | TNNLS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9046288) | - |\n| 2020 | **深度学习用于社区发现：进展、挑战与机遇** | IJCAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.08225) | - |\n| 2018 | **基于深度学习的聚类综述：从网络架构视角** | IEEE Access | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=8412085) | - |\n\n\n\n\n\n## 论文\n\n### 基于 LLM 的深度图聚类\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ |:-----:| :----------------------------------------------------------: |:----:|\n| 2024 | **大型语言模型引导的图聚类** | LOG | [链接](https:\u002F\u002Fopenreview.net\u002Fpdf?id=CLyhlb5DG5) | - |\n\n\n### 新架构深度图聚类\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **用于图上归一化割的扩张层次结构** | KDD |[链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3637528.3671978) | https:\u002F\u002Fzenodo.org\u002Frecords\u002F12108189 | \n| 2024 | **用于图的科尔莫戈洛夫-阿诺德网络（KAN）** | - | - | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FKAN4Graph) |\n\n\n### 时序深度图聚类\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **基于图的时间序列聚类，用于端到端分层预测** | arxiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.19183) | - |\n| 2024 | **深度时序图聚类（TGC）** | ICLR | [链接](https:\u002F\u002Fopenreview.net\u002Fpdf?id=ViNe1fjGME) | [链接](https:\u002F\u002Fgithub.com\u002FMGitHubL\u002FTGC) |\n\n### 聚类数目未知的深度图聚类\n\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **NeuroCUT：一种鲁棒的图划分神经方法** | KDD | [链接](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3637528.3671815) | [链接](https:\u002F\u002Fgithub.com\u002Fidea-iitd\u002FNeuroCut) |\n| 2024 | **LSEnet：用于深度图聚类的洛伦兹结构熵神经网络（LSEnet）** | ICML | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2405.11801) | [链接](https:\u002F\u002Fgithub.com\u002FZhenhHuang\u002FLSEnet\u002Ftree\u002Fmain) |\n| 2024 | **无预先指定聚类数 k 的图聚类掩码自编码器（GCMA）** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2401.04741.pdf) | - |\n| 2023 | **聚类数目未知的强化图聚类（RGC）** | ACM MM | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.06827) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FRGC) \n\n\n\n\n\n### 重构型深度图聚类\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **协同深度图聚类网络（SynC）** | Arxiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2406.15797) | [链接](https:\u002F\u002Fgithub.com\u002FMarigoldwu\u002FSynC) | \n| 2024 | **深度掩码图节点聚类（DMGC）** | TCSS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10550181) | - |\n| 2024 | **多尺度图聚类网络（MGCN）** | IS | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS002002552400937X) | [链接](https:\u002F\u002Fgithub.com\u002FZj202309\u002FMGCN) | \n| 2024 | **基于在线互学习的端到端深度图聚类** | TNNLS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10412657) | - |\n| 2024 | **用于社区发现的对比深度非负矩阵分解（CDNMF）** | ICASSP | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.02357) | [链接](https:\u002F\u002Fgithub.com\u002F6lyc\u002FCDNMF) |\n| 2023 | **EGRC-Net：嵌入诱导的图精炼聚类网络（EGRC-Net）** | TIP | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=10326461) | [链接](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FTIP23---EGRC-Net) |\n| 2023 | **超越证据下界：用于节点聚类的对偶变分图自编码器（BELBO-VGAE）** | SDM | [链接](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fpdf\u002F10.1137\u002F1.9781611977653.ch12) | [链接](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FBELBO-VGAE) |\n| 2023 | **基于图神经网络的图聚类（DMoN）** | JMLR | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.16904) | [链接](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002Fgraph_embedding\u002Fdmon) |\n| 2023 | **结构嵌入增强的图聚类网络（GC-SEE）** | PR | [链接](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2023.109833) | [链接](https:\u002F\u002Fgithub.com\u002FMarigoldwu\u002FGC-SEE) |\n| 2023 | **超越同质性：为图无关聚类重建结构（DGCN）** | ICML | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.02931) | [链接](https:\u002F\u002Fgithub.com\u002FPanern\u002FDGCN) |\n| 2023 | **走向凸流形：单细胞RNA-seq数据深度图聚类的几何视角（scTCM）** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F0540.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FMMAMAR\u002FscTConvexMan) |\n| 2023 | **探索局部与全局潜在配置的交互作用以进行单细胞RNA-seq聚类：统一视角（scTPF）** | AAAI | [链接](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F26107) | [链接](https:\u002F\u002Fgithub.com\u002FMMAMAR\u002FscTPF) |\n| 2022 | **逃离特征扭曲：用于节点聚类的变分图自编码器（FT-VGAE）** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2022\u002F465) | [链接](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FFT-VGAE) |\n| 2022 | **深度注意力引导的双自监督图聚类（DAGC）** | TCSVT | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=9999681) | [链接](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FDAGC) |\n| 2022 | **重新思考属性图聚类的图自编码器模型（R-GAE）** | TKDE | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2107.08562) | [链接](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FR-GAE) |\n| 2022 | **图嵌入聚类：具有簇特异性分布的图注意力自编码器（GEC-CSD）** | NN | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0893608021002008) | - |\n| 2022 | **通过网络嵌入探索时间社区结构（VGRGMM）** | TCYB | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9768181) | - |\n| 2022 | **聚类感知的异构信息网络嵌入（VaCA-HINE）** | WSDM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498385) | - |\n| 2022 | **用于联合节点表示学习和聚类的有效图卷积（GCC）** | WSDM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3488560.3498533) | [链接](https:\u002F\u002Fgithub.com\u002Fchakib401\u002Fgraph_convolutional_clustering) |\n| 2022 | **基于ZINB的单细胞RNA-seq解释用图嵌入自编码器（scTAG）** | AAAI | [链接](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-5060.YuZ.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FPhilyzh8\u002FscTAG) |\n| 2022 | **图社区信息最大化（GCI）** | TKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3480244) | - |\n| 2022 | **多级子空间融合的深度图聚类（DGCSF）** | PR | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS003132032200557X) | - |\n| 2022 | **基于变分图嵌入的图聚类（GC-VAE）** | PR | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0031320321005148) | - |\n| 2022 | **深度邻居感知嵌入用于属性图中的节点聚类（DNENC）** | PR | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0031320321004118) | - |\n| 2022 | **协作决策强化的属性图聚类自监督（CDRS）** | TNNLS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9777842) | [链接](https:\u002F\u002Fgithub.com\u002FJillian555\u002FTNNLS_CDRS) |\n| 2022 | **用于图聚类的嵌入图自编码器（EGAE）** | TNNLS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9741755) | [链接](https:\u002F\u002Fgithub.com\u002Fhyzhang98\u002FEGAE) |\n| 2021 | **用于多视图聚类的自监督图卷积网络（SGCMC）** | TMM | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9472979\u002F) | [链接](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FSGCMC) |\n| 2021 | **用于关系数据聚类的适应性超图自编码器（AHGAE）** | TKDE | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fiel7\u002F69\u002F4358933\u002F09525190.pdf%3Fcasa_token%3DmbL8SLkmu8AAAAAA:mNPoE2n3BwaMZsYdRotHwa8Qs3uyzY53ZPVd0ixXutwqovM4vA7OSmsYWN3qXOAGW3CgH-LugHo&hl=en&sa=T&oi=ucasa&ct=ucasa&ei=_dvpYcTXCcCVy9YPgta4-AM&scisig=AAGBfm2V50SkaPV0K8x2F_mYsC15x028wA) | - | \n| 2021 | **注意力驱动的图聚类网络（AGCN）** | ACM MM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3474085.3475276?casa_token=P8cfxVYUtDYAAAAA:J3wHvLHJKu18558Us6rUHjgxXztBqOYMeNNuqFesIflTJiOefWkz8k2xnNzxJYfDYUyUP8BkUrazKA) | [链接](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FMM21---AGCN) |\n| 2021 | **深度融合聚类网络（DFCN）** | AAAI | [链接](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17198\u002F17005) | [链接](https:\u002F\u002Fgithub.com\u002FWxTu\u002FDFCN) |\n| 2020 | **协作图卷积网络：无监督学习与半监督学习的结合（CGCN）** | AAAI | [链接](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fdownload\u002F5843\u002F5699) | [链接](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FR-GAE\u002Ftree\u002Fmaster\u002FGMM-VGAE) |\n| 2020 | **基于注意力跨图关联的深度多图聚类（DMGC）** | WSDM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3336191.3371806) | [链接](https:\u002F\u002Fgithub.com\u002Fflyingdoog\u002FDMGC) |\n| 2020 | **深入探索：图卷积梯形网络（GCLN）** | AAAI | [链接](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5673\u002F5529) | - |\n| 2020 | **用于聚类的多视图属性图卷积网络（MAGCN）** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0411.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FIMKBLE\u002FMAGCN) |\n| 2020 | **用于多视图图聚类的One2Multi图自编码器（O2MAC）** | WWW | [链接](http:\u002F\u002Fshichuan.org\u002Fdoc\u002F83.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fgooglebaba\u002FWWW2020-O2MAC) |\n| 2020 | **结构化深度聚类网络（SDCN\u002FSDCN_Q）** | WWW | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.01633) | [链接](https:\u002F\u002Fgithub.com\u002Fbdy9527\u002FSDCN) |\n| 2020 | **狄利克雷图变分自编码器（DGVAE）** | NeurIPS | [链接](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Ffile\u002F38a77aa456fc813af07bb428f2363c8d-Paper.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fxiyou3368\u002FDGVAE) |\n| 2019 | **RWR-GAE：用于图自编码器的随机游走正则化（RWR-GAE）** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.04003) | [链接](https:\u002F\u002Fgithub.com\u002FMysteryVaibhav\u002FRWR-GAE) |\n| 2019 | **用于无监督图表示学习的对称图卷积自编码器（GALA）** | ICCV | [链接](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fpapers\u002FPark_Symmetric_Graph_Convolutional_Autoencoder_for_Unsupervised_Graph_Representation_Learning_ICCV_2019_paper.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fsseung0703\u002FGALA_TF2.0) |\n| 2019 | **属性图聚类：一种深度注意力嵌入方法（DAEGC）** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0509.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FTiger101010\u002FDAEGC) |\n| 2019 | **用于属性网络嵌入的网络特定变分自编码器（NetVAE）** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F370) | - |\n| 2017 | **动态嵌入的图聚类（GRACE）** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.08249) | [链接](https:\u002F\u002Fgithub.com\u002Fyangji9181\u002FGRACE?utm_source=catalyzex.com) | \n| 2017 | **MGAE：用于图聚类的边缘化图自编码器（MGAE）** | CIKM | [链接](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FShirui-Pan-3\u002Fpublication\u002F320882195_MGAE_Marginalized_Graph_Autoencoder_for_Graph_Clustering\u002Flinks\u002F5b76157b45851546c90a3d74\u002FMGAE-Marginalized-Graph-Autoencoder-for-Graph-Clustering.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FMGAE) |\n| 2017 | **在图上同时进行社区检测与节点嵌入以学习社区嵌入（ComE）** | CIKM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3132847.3132925?casa_token=R5eF-os9QxQAAAAA:GFW1TYwX8Yfs7ytT7tiVsAbNDJZhy0ZAVxzx3vYNBlKuwUKthV6OUuF0SdaKSX1DUMXVtr61SlJg0Q) | [链接](https:\u002F\u002Fgithub.com\u002Fvwz\u002FComE) |\n| 2016 | **用于学习图表示的深度神经网络（DNGR）** | AAAI | [链接](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fdownload\u002F10179\u002F10038) | [链接](https:\u002F\u002Fgithub.com\u002FShelsonCao\u002FDNGR) |\n| 2015 | **基于深度架构的异构网络嵌入（HNE）** | SIGKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F2783258.2783296?casa_token=HCfko1SoHs0AAAAA:e5B7ZeoGp2DcuT5kj8KwnghRnMyQhoGhWhDEQoSCI6CkuhtIGshlvZzjLQT2c0LHO8R2jo_4KkVOuQ) | - |\n| 2014 | **用于图聚类的学习深度表示（GraphEncoder）** | AAAI | [链接](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F8916\u002F8775) | [链接](https:\u002F\u002Fgithub.com\u002Fquinngroup\u002Fdeep-representations-clustering) |\n\n### 对抗性深度图聚类\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :----: | :--------------------------------------------------------: | :--------------------------------------------: |\n| 2023 | **Wasserstein对抗正则化图自编码器（WARGA）** | Neurocomputing | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2111.04981) | [链接](https:\u002F\u002Fgithub.com\u002FLeonResearch\u002FWARGA) |\n| 2022 | **超越同质性的无监督网络嵌入（SELENE）** | TMLR | [链接](https:\u002F\u002Forbilu.uni.lu\u002Fbitstream\u002F10993\u002F53475\u002F1\u002FTMLR22b.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fzhiqiangzhongddu\u002FSELENE) |\n| 2020 | **JANE：联合对抗网络嵌入（JANE）** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0192.pdf) | - |\n| 2019 | **用于集成聚类的对抗图嵌入（AGAE）** | IJCAI | [链接](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10113653) | - |\n| 2019 | **CommunityGAN：基于生成对抗网络的社区发现（CommunityGAN）** | WWW | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3308558.3313564) | [链接](https:\u002F\u002Fgithub.com\u002FSamJia\u002FCommunityGAN) |\n| 2019 | **ProGAN：通过邻近关系生成对抗网络进行网络嵌入（ProGAN）** | SIGKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3292500.3330866) | - |\n| 2019 | **利用对抗训练方法学习图嵌入（ARGA\u002FARVGA）** | TCYB | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.01250) | [链接](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FARGA) |\n| 2019 | **用于图嵌入的对抗正则化图自编码器（ARGA\u002FARVGA）** | IJCAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.04407) | [链接](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FARGA) |\n\n\n\n\n### 对比学习深度图聚类\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :-----: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **重新审视图聚类中的模块度最大化：对比学习视角** | SIGKDD | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2406.14288) | [链接](https:\u002F\u002Fgithub.com\u002FEdisonLeeeee\u002FMAGI?tab=readme-ov-file) |\n| 2024 | **GLAC-GCN：全局与局部拓扑感知的对比图聚类网络 (GLAC-GCN)** | TAI | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10557452) | [链接](https:\u002F\u002Fgithub.com\u002Fxuyuankun631\u002FGLAC-GCN) |\n| 2024 | **具有自适应编码器的多视图属性图对比聚类** | TNNLS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10509800) | - |\n| 2024 | **用于社区发现的对比深度非负矩阵分解 (CDNMF)** | ICASSP | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.02357) | [链接](https:\u002F\u002Fgithub.com\u002F6lyc\u002FCDNMF) |\n| 2023 | **用于节点聚类的对比变分图自编码器 (CVGAE)** | PR | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0031320323009068) | [链接](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FCVGAE_PR) | \n| 2023 | **用于图聚类的双对比学习网络** | TNNLS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10097557) | [链接](https:\u002F\u002Fgithub.com\u002FXinPeng97\u002FTNNLS_DCLN) | \n| 2023 | **带有保簇增强的对比学习用于属性图聚类** | ECML-PKDD | [链接](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-031-43412-9_38) | - | \n| 2023 | **具有输入感知和簇感知正则化的图对比表示学习** | ECML-PKDD | [链接](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-031-43415-0_39) | - |\n| 2023 | **未知簇数的强化图聚类 (RGC)** | ACM MM | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.06827) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FRGC) \n| 2023 | **自对比图扩散网络** | ACM MM | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2307.14613.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fkunzhan\u002FSCDGN) \n| 2023 | **CONVERT：基于可靠增强的对比图聚类 (CONVERT)** | ACM MM | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.08963.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fxihongyang1999\u002FCONVERT) |\n| 2023 | **通过可学习增强进行属性图聚类 (AGCLA)** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2212.03559.pdf) | - |\n| 2023 | **加速图上表示学习的聚类方法 (CARL-G)** | SIGKDD | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2306.06936.pdf) | - |\n| 2023 | **Dink-Net：大规模图上的神经网络聚类 (Dink-Net)** | ICML | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.18405.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FDink-Net) |\n| 2023 | **CONGREGATE：曲率空间中的对比图聚类 (CONGREGATE)**| IJCAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.03555.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FCurvCluster\u002FCongregate) |\n| 2023 | **多层级图对比原型聚类**| IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2023\u002F0513.pdf) | - | \n| 2023 | **简单对比图聚类 (SCGC)** | TNNLS | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.07865) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FSCGC) |\n| 2023 | **硬样本感知的对比深度图聚类网络 (HSAN)** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.08665) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FHSAN) |\n| 2023 | **簇引导的对比图聚类网络 (CCGC)** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.01098) | [链接](https:\u002F\u002Fgithub.com\u002Fxihongyang1999\u002FCCGC) |\n| 2022 | **NCAGC：用于属性图聚类的邻域对比框架 (NCAGC)** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.07897) | [链接](https:\u002F\u002Fgithub.com\u002Fwangtong627\u002FDual-Contrastive-Attributed-Graph-Clustering-Network) |\n| 2022 | **SCGC：自监督对比图聚类 (SCGC)** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2204.12656) | [链接](https:\u002F\u002Fgithub.com\u002Fgayanku\u002FSCGC) |\n| 2022 | **改进的双重相关性减少网络 (IDCRN)** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.12533) | - |\n| 2022 | **面向异质性的图自监督学习 (HGRL)** | CIKM | [链接](https:\u002F\u002Fscholar.archive.org\u002Fwork\u002Fchm4lsfonvbfree7n36vqlcl4a\u002Faccess\u002Fwayback\u002Fhttps:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3511808.3557478) | [链接](https:\u002F\u002Fgithub.com\u002FyifanQi98\u002FHGRL) |\n| 2022 | **S3GC：可扩展的自监督图聚类 (S3GC)** | NeurIPS | [链接](https:\u002F\u002Fopenreview.net\u002Fforum?id=ldl2V3vLZ5) | [链接](https:\u002F\u002Fgithub.com\u002Fdevvrit\u002FS3GC) |\n| 2022 | **带有伪标签提示的自一致属性图对比聚类 (SCAGC)** | TMM | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.08264) | [链接](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FSCAGC) |\n| 2022 | **CGC：用于社区检测与追踪的对比图聚类 (CGC)** | WWW | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.08504) | - |\n| 2022 | **无监督深度图结构学习 (SUBLIME)** | WWW | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2201.06367.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FGRAND-Lab\u002FSUBLIME) |\n| 2022 | **具有双重冗余减少的属性图聚类 (AGC-DRR)** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2022\u002F0418.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fgongleii\u002FAGC-DRR) |\n| 2022 | **通过双重相关性减少进行深度图聚类 (DCRN)** | AAAI | [链接](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-5928.LiuY.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FDCRN) |\n| 2022 | **RepBin：基于约束的宏基因组分箱用图表示学习 (RepBin)** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2112.11696.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fxuehansheng\u002FRepBin) |\n| 2022 | **无增强的图自监督学习 (AFGRL)** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2112.02472) | [链接](https:\u002F\u002Fgithub.com\u002FNamkyeong\u002FAFGRL) |\n| 2022 | **SAIL：自我增强的图对比学习 (SAIL)** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.00934) | - |\n| 2021 | **具有联合表示聚类的去偏图对比学习 (GDCL)** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0473.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fhzhao98\u002FGDCL) |\n| 2021 | **多视图对比图聚类 (MCGC)** | NeurIPS | [链接](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F2021\u002Ffile\u002F10c66082c124f8afe3df4886f5e516e0-Paper.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fpanern\u002Fmcgc) |\n| 2021 | **具有协同对比学习的自监督异质图神经网络 (HeCo)** | SIGKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467415) | [链接](https:\u002F\u002Fgithub.com\u002Fliun-online\u002FHeCo) |\n| 2020 | **用于属性图嵌入的自适应图编码器 (AGE)** | SIGKDD | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.01594) | [链接](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FAGE) |\n| 2020 | **CommDGI：面向社区检测的深度图信息最大化的模型 (CommDGI)** | CIKM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412042) | [链接](https:\u002F\u002Fgithub.com\u002FFDUDSDE\u002FCommDGI) |\n| 2020 | **图上的多视图对比表示学习 (MVGRL)** | ICML | [链接](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fhassani20a\u002Fhassani20a.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fkavehhassani\u002Fmvgrl) |\n\n### 应用\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :---------: | :----------------------------------------------------------: | :--: |\n| 2024 | **EyeGraph：面向模块性的时空图聚类，用于连续事件驱动的眼动追踪** | NeurIPS | [链接](https:\u002F\u002Fink.library.smu.edu.sg\u002Fcgi\u002Fviewcontent.cgi?params=\u002Fcontext\u002Fsis_research\u002Farticle\u002F10909\u002F&path_info=2367_EyeGraph_Modularity_aware.pdf) | - | \n| 2024 | **先识别再推荐：迈向无监督的群体推荐（ITR）** | NeurIPS | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.23757) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FITR) | \n| 2024 | **面向推荐中意图学习的端到端可学习聚类（ELCRec）** | NeurIPS | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2401.05975.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FELCRec) | \n| 2023 | **GuardFL：通过带属性的客户端图聚类防御联邦学习中的后门攻击** | TIFS | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F11275861) | [链接](https:\u002F\u002Fgithub.com\u002Fcsyuhao\u002FGuardFL-Official) |\n\n\n### 其他\n\n\n| 年份 | 标题 | 会议\u002F期刊 | 论文 | 代码 |\n| ---- | ------------------------------------------------------------ | :----: | :--------------------------------------------------------: | :--------------------------------------------: |\n| 2023 | **基于元学习的鲁棒图聚类，用于处理噪声图（MetaGC）** | CIKM | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.00322) | [链接](https:\u002F\u002Fgithub.com\u002FHyeonsooJo\u002FMetaGC) |\n\n\n\n## 其他相关论文\n\n### 深度聚类\n\n| 年份 | 标题 | **会议\u002F期刊** | 论文 | 代码 |\n| :--: | :----------------------------------------------------------- | :-------: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **ProCom：一种少样本目标社区检测算法** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2408.07369) | [链接](https:\u002F\u002Fgithub.com\u002FWxxShirley\u002FKDD2024ProCom?tab=readme-ov-file) | \n| 2024 | **通过融合社区结构与邻居信息的深度图聚类（DIGC）** | IS | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS002002552400865X) | - |\n| 2024 | **信息增强型深度图聚类网络（IEDGCN）** | Neurocomputing | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092523122400763X) | - |\n| 2024 | **每个节点都不同：为属性图聚类动态融合自监督任务** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2401.06595v1) | [链接](https:\u002F\u002Fgithub.com\u002Fq086\u002FDyFSS) | \n| 2024 | **DGCLUSTER：一种基于模块度最大化的属性图聚类神经框架（DGCluster）** | AAAI | [链接](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F28983) | - |\n| 2023 | **用于属性图聚类的互增强网络（MBN）**| KBS | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417423009818) | - |\n| 2023 | **面向图聚类的无冗余自监督关系学习**| TNNLS | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2309.04694.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fyisiyu95\u002FR2FGC) |\n| 2023 | **属性多关系图的谱聚类**| SIGKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3447548.3467381) | - |\n| 2023 | **带有噪声标签的局部图聚类**| Arxiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2310.08031.pdf) | - |\n| 2023 | **对属性图聚类深度学习方法的重新评估**| CIKM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3583780.3614768) | [链接](https:\u002F\u002Fgithub.com\u002F2100271064\u002FA-Re-evaluation-of-Deep-Learning-Methods-for-Attributed-Graph-Clustering) |\n| 2023 | **基于元加权的鲁棒图聚类，适用于噪声图**| CIKM | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2311.00322.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FHyeonsooJo\u002FMetaGC) |\n| 2023 | **同质性增强的图聚类结构学习**| CIKM | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.05309.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fgalogm\u002FHoLe) |\n| 2023 | **对属性图聚类深度学习方法的重新评估** | CIKM | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3583780.3614768) | [链接](https:\u002F\u002Fgithub.com\u002F2100271064\u002FA-Re-evaluation-of-Deep-Learning-Methods-for-Attributed-Graph-Clustering) |\n| 2023 | **超越证据下界：用于节点聚类的双变分图自编码器** | SDM | [链接](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977653.ch12) | [链接](https:\u002F\u002Fgithub.com\u002Fnairouz\u002FBELBO-VGAE) |\n| 2023 | **GC-Flow：一种基于图的流网络，用于高效聚类** | ICLM | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.17284.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fxztcwang\u002FGCFlow) |\n| 2023 | **可扩展的属性图子空间聚类（SAGSC）** | AAAI | [链接](https:\u002F\u002Fchakib401.github.io\u002Ffiles\u002FSAGSC.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fchakib401\u002Fsagsc) |\n| 2022 | **自适应属性与结构子空间聚类网络（AASSC-Net）** | TIP | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fiel7\u002F83\u002F9626658\u002F09769915.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FZhihaoPENG-CityU\u002FTIP22---AASSC-Net) |\n| 2022 | **孪生对比学习用于在线聚类** | IJCV | [链接](http:\u002F\u002Fpengxi.me\u002Fwp-content\u002Fuploads\u002F2022\u002F07\u002FTwin-Contrastive-Learning-for-Online-Clustering.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FYunfan-Li\u002FTwin-Contrastive-Learning) |\n| 2022 | **通过O(n)二分图卷积进行非图数据聚类** | TPAMI | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9996549) | [链接](https:\u002F\u002Fgithub.com\u002Fhyzhang98\u002FAnchorGAE-torch) |\n| 2022 | **Ada-nets：通过在结构空间中自适应发现邻居进行人脸聚类** | ICLR | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.03800) | [链接](https:\u002F\u002Fgithub.com\u002Fdamo-cv\u002FAda-NETS) |\n| 2021 | **用于通用数据聚类的自适应图自编码器** | TPAMI | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9606581) | [链接](https:\u002F\u002Fgithub.com\u002Fhyzhang98\u002FAdaGAE) |\n| 2021 | **对比聚类** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.09687.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FYunfan-Li\u002FContrastive-Clustering) |\n| 2017 | **迈向适合k-means的空间：同步深度学习与聚类（DCN）** | ICML | [链接](http:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Fyang17b\u002Fyang17b.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fboyangumn\u002FDCN) |\n| 2017 | **改进的局部结构保持深度嵌入式聚类（IDEC）** | IJCAI | [链接](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FXifeng-Guo\u002Fpublication\u002F317095655_Improved_Deep_Embedded_Clustering_with_Local_Structure_Preservation\u002Flinks\u002F59263224458515e3d4537edc\u002FImproved-Deep-Embedded-Clustering-with-Local-Structure-Preservation.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FXifengGuo\u002FIDEC) |\n| 2016 | **用于聚类分析的无监督深度嵌入（DEC）** | ICML | [链接](http:\u002F\u002Fproceedings.mlr.press\u002Fv48\u002Fxieb16.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fpiiswrong\u002Fdec) |\n\n\n\n### 深度层次聚类\n\n| 年份 | 标题 | **会议\u002F期刊** | 论文 | 代码 |\n| :--: | :----------------------------------------------------------- | :-------: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2023 | **对比层次聚类（CHC）**| ECML PKDD | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.03389) | [链接](https:\u002F\u002Fgithub.com\u002FMichalZnalezniak\u002FContrastive-Hierarchical-Clustering) |\n\n\n\n### 其他相关方法\n\n| 年份 | 标题 | **会议\u002F期刊** | 论文 | 代码 |\n| :--: | :----------------------------------------------------------- | :-------: | :----------------------------------------------------------: | :----------------------------------------------------------: |\n| 2024 | **PSMC：基于模体导纳的图聚类可证明且可扩展算法**|KDD | [链接](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3637528.3671666) | - |\n| 2024 | **大规模属性二分图上的有效聚类（TPO）** | arXiv | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3637528.3671764) | - |\n| 2023 | **GPUSCAN++：GPU上的高效结构化图聚类** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2311.12281.pdf) | - |\n| 2022 | **用于属性图聚类的深度线性图注意力模型** | Knowl Based Syst | [链接](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.108665) | - |\n| 2022 | **基于随机游走的自监督学习的可扩展深度图聚类** | WWW | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2112.15530) | - |\n| 2022 | **X-GOAL：多层异构图原型对比学习（X-GOAL）** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.03560) | - |\n| 2022 | **基于多级子空间融合的深度图聚类** | PR | [链接](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2022.109077) |-|\n| 2022 | **GRACE：用于属性图聚类的通用图卷积框架** | TKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3544977) | [链接](https:\u002F\u002Fgithub.com\u002FBarakeelFanseu\u002FGRACE) | |\n| 2022 | **细粒度属性图聚类** | SDM | [链接](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977172.42) | [链接](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FFGC) |\n| 2022 | **多视图图嵌入聚类网络：联合自监督与块对角表示** | NN | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS089360802100397X?via%3Dihub) | [链接](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FNN-2022-MVGC) |\n| 2022 | **SAGES：用于无监督学习的采样式可扩展属性图嵌入** | TKDE | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9705119) | - |\n| 2022 | **图的自动化自监督学习** | ICLR | [链接](https:\u002F\u002Fopenreview.net\u002Fforum?id=rFbR4Fv-D6-) | [链接](https:\u002F\u002Fgithub.com\u002FChandlerBang\u002FAutoSSL) |\n| 2022 | **用于多视图聚类的平稳扩散状态神经估计** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.01334) | [链接](https:\u002F\u002Fgithub.com\u002Fkunzhan\u002FSDSNE) |\n| 2021 | **简单谱图卷积** | ICLR | [链接](https:\u002F\u002Fopenreview.net\u002Fpdf?id=CYO5T-YjWZV) | [链接](https:\u002F\u002Fgithub.com\u002Fallenhaozhu\u002FSSGC) |\n| 2021 | **用于属性图聚类的谱嵌入网络（SENet）** | NN | [链接](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0893608021002227) | - |\n| 2021 | **平滑度传感器：用于属性图聚类的自适应平滑过渡图卷积** | TCYB | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9514513) | [链接](https:\u002F\u002Fgithub.com\u002FaI-area\u002FNASGC) |\n| 2021 | **多视图属性图聚类** | TKDE | [链接](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FZhao-Kang-6\u002Fpublication\u002F353747180_Multi-view_Attributed_Graph_Clustering\u002Flinks\u002F612059cd0c2bfa282a5cd55e\u002FMulti-view-Attributed-Graph-Clustering.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FMAGC) |\n| 2021 | **高阶深度多路信息最大化** | WWW | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07810) | [链接](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FHDMI) |\n| 2021 | **图InfoClust：在图中最大化粗粒度互信息** | PAKDD | [链接](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-030-75762-5_43) | [链接](https:\u002F\u002Fgithub.com\u002Fcmavro\u002FGraph-InfoClust-GIC) |\n| 2021 | **基于图滤波器的多视图属性图聚类** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0375.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FMvAGC) |\n| 2021 | **Graph-MVP：用于多层图的多视图原型对比学习** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.03560) | [链接](https:\u002F\u002Fgithub.com\u002Fchao1224\u002FGraphMVP) |\n| 2021 | **对比拉普拉斯特征映射** | NeurIPS | [链接](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002F2d1b2a5ff364606ff041650887723470-Paper.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fallenhaozhu\u002FCOLES) |\n| 2020 | **面向无监督图表示学习的聚类感知图神经网络** | arXiv | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01674) | - |\n| 2020 | **分布诱导的双向GAN用于图表示学习** | CVPR | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1912.01899) | [链接](https:\u002F\u002Fgithub.com\u002FSsGood\u002FDBGAN) |\n| 2020 | **带有注意力机制的自适应图卷积网络用于共同显著性检测的图聚类** | CVPR | [链接](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2020\u002Fpapers\u002FZhang_Adaptive_Graph_Convolutional_Network_With_Attention_Graph_Clustering_for_Co-Saliency_CVPR_2020_paper.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fltp1995\u002FGCAGC-CVPR2020) |\n| 2020 | **利用图神经网络进行图池化的谱聚类（MinCutPool）** | ICML | [链接](http:\u002F\u002Fproceedings.mlr.press\u002Fv119\u002Fbianchi20a\u002Fbianchi20a.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FFilippoMB\u002FSpectral-Clustering-with-Graph-Neural-Networks-for-Graph-Pooling) |\n| 2020 | **MAGNN：用于异质图嵌入的元路径聚合图神经网络** | WWW | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.01680) | [链接](https:\u002F\u002Fgithub.com\u002Fcynricfu\u002FMAGNN) |\n| 2020 | **无监督属性多层网络嵌入** | AAAI | [链接](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.06750) | [链接](https:\u002F\u002Fgithub.com\u002Fpcy1302\u002FDMGI) |\n| 2020 | **跨图：鲁棒且无监督的属性图嵌入，适用于结构受损的图** | ICDM | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9338269) | [链接](https:\u002F\u002Fgithub.com\u002FFakeTibbers\u002FCross-Graph) |\n| 2020 | **多分类不平衡图卷积网络学习** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0398.pdf) | - |\n| 2020 | **CAGNN：面向无监督图表示学习的聚类感知图神经网络** | arXiv | [链接](http:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01674) | - |\n| 2020 | **通过深度自适应图最大化进行属性图聚类** | ICCKE | [链接](https:\u002F\u002Fieeexplore-ieee-org-s.nudtproxy.yitlink.com\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9303694) | - |\n| 2019 | **异质图注意力网络（HAN）** | WWW | [链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.07293.pdf) | [链接](https:\u002F\u002Fgithub.com\u002FJhy1993\u002FHAN) |\n| 2019 | **多视图一致性图聚类** | TIP | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8501973) | [链接](https:\u002F\u002Fgithub.com\u002Fkunzhan\u002FMCGC) |\n| 2019 | **通过自适应图卷积（AGC）进行属性图聚类** | IJCAI | [链接](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0601.pdf) | [链接](https:\u002F\u002Fgithub.com\u002Fkarenlatong\u002FAGC-master) |\n| 2016 | **node2vec：面向网络的可扩展特征学习（node2vec）** | SIGKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F2939672.2939754?casa_token=jt4dhGo-tKEAAAAA:lhscLc-u0XZFYYyi48kXK3_vtYR-PffsbbMRZdtpbaprcB1FGyjWH1RvstHACYALyZ9OtUf2nv_FjQ) | [链接](http:\u002F\u002Fsnap.stanford.edu\u002Fnode2vec\u002F) |\n| 2016 | **变分图自动编码器（GAE）** | NeurIPS Workshop | [链接](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9046288) | [链接](https:\u002F\u002Fgithub.com\u002Ftkipf\u002Fgae) |\n| 2015 | **LINE：大规模信息网络嵌入（LINE）** | WWW | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F2736277.2741093?casa_token=ahQ9yUhknkAAAAAA:lP6rusbODmZ1ZpGxF-cIiiopMiAA8Q4I02cBBbfE5dc8-NQpiPOdV0cv4-43lA9CkTXU4mPei39UDg) | [链接](https:\u002F\u002Fgithub.com\u002Ftangjianpku\u002FLINE) |\n| 2014 | **DeepWalk：社交表征的在线学习（DeepWalk）** | SIGKDD | [链接](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F2623330.2623732?casa_token=x6Gui_HExYoAAAAA:mzfm0BH0rSX7qcQV2WJ6uTSsg7zjnPalmOQ8sQuoJrwXfh9fcDgVPgXb-APCLGk1qWsPpIkBhI61pw) | [链接](https:\u002F\u002Fgithub.com\u002Fphanein\u002Fdeepwalk) |\n\n## 基准数据集\n\n我们将数据集分为两类：图数据集和非图数据集。图数据集是现实世界中的各类图结构，例如引用网络、社交网络等。非图数据集则不属于图类型。不过，在必要时，我们可以通过K近邻（KNN）算法构建“邻接矩阵”。\n\n\n\n#### 快速入门\n\n- 第一步：从以下链接下载所有数据集：[[Google Drive](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1thSxtAexbvOyjx-bJre8D4OyFKsBe1bK?usp=sharing) | [坚果云](https:\u002F\u002Fwww.jianguoyun.com\u002Fp\u002FDfzK1pwQwdaSChjI2aME)]。也可选择从表格中的Google Drive链接单独下载部分数据集。\n- 第二步：将压缩包解压至**.\u002Fdataset\u002F**目录下。\n- 第三步：在**main.py**中修改数据集的类型和名称。\n- 第四步：运行**main.py**。\n\n\n\n#### 代码\n\n- **utils.py**\n 1. **load_graph_data**：加载图数据集\n 2. **load_data**：加载非图数据集\n 3. **normalize_adj**：对邻接矩阵进行归一化\n 4. **diffusion_adj**：计算图扩散矩阵\n 5. **construct_graph**：为非图数据集构建KNN图\n 6. **numpy_to_torch**：将NumPy数组转换为PyTorch张量\n 7. **torch_to_numpy**：将PyTorch张量转换为NumPy数组\n- **clustering.py**\n 1. **setup_seed**：固定随机种子\n 2. **evaluation**：评估聚类性能\n 3. **k_means**：K均值算法\n- **visualization.py**\n 1. **t_sne**：t-SNE算法\n 2. **similarity_plot**：可视化嵌入或特征的余弦相似度矩阵\n\n\n\n#### 数据集详情\n\n关于每个数据集的介绍，请参阅[此处](.\u002Fdataset\u002FREADME.md)。\n\n1. 图数据集\n\n | 数据集 | 样本数 | 维度 | 边数 | 类别数 | 链接 |\n | :------: | :-------: | :---------: | :-----: | :-------: | :----------------------------------------------------------: |\n | CORA | 2708 | 1433 | 5278 | 7 | [cora.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1_LesghFTQ02vKOBUfDP8fmDF1JP3MPrJ\u002Fview?usp=sharing) |\n | CITESEER | 3327 | 3703 | 4552 | 6 | [citeseer.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1dEsxq5z5dc35tS3E46pg6pc2LUMlF6jF\u002Fview?usp=sharing) |\n | CITE | 3327 | 3703 | 4552 | 6 | [cite.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1dEsxq5z5dc35tS3E46pg6pc2LUMlF6jF\u002Fview?usp=sharing) |\n | PUBMED | 19717 | 500 | 44324 | 3 | [pubmed.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1tdr20dvvjZ9tBHXj8xl6wjO9mQzD0rzA\u002Fview?usp=sharing) |\n | DBLP | 4057 | 334 | 3528 | 4 | [dblp.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1XWWMIDyvCQ4VJFnAmXS848ksN9MFm5ys\u002Fview?usp=sharing) |\n | ACM | 3025 | 1870 | 13128 | 3 | [acm.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F19j7zmQ-AMgzTX7yZoKzUK5wVxQwO5alx\u002Fview?usp=sharing) |\n | AMAP | 7650 | 745 | 119081 | 8 | [amap.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1qqLWPnBOPkFktHfGMrY9nu8hioyVZV31\u002Fview?usp=sharing) |\n | AMAC | 13752 | 767 | 245861 | 10 | [amac.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1DJhSOYWXzlRDSTvaC27bSmacTbGq6Ink\u002Fview?usp=sharing) |\n | CORAFULL | 19793 | 8710 | 63421 | 70 | [corafull.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1XLqs084J3xgWW9jtbBXJOmmY84goT1CE\u002Fview?usp=sharing) |\n | WIKI | 2405 | 4973 | 8261 | 17 | [wiki.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1vxupFQaEvw933yUuWzzgQXxIMQ_46dva\u002Fview?usp=sharing) |\n | COCS | 18333 | 6805 | 81894 | 15 | [cocs.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F186twSfkDNmqh9L618iCeWq4DA7Lnpte0\u002Fview?usp=sharing) |\n | CORNELL | 183 | 1703 | 149 | 5 | [cornell.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1EjpHP26Oh0_qHl13vOfEzc4ZyzkGrR-M\u002Fview?usp=sharing) |\n | TEXAS | 183 | 1703 | 162 | 5 | [texas.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1kpz6b9-OsEU1RsAyxWWeUgzhdd3-koI2\u002Fview?usp=sharing) |\n | WISC | 251 | 1703 | 257 | 5 | [wisc.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1I8v1H1IthEiWd4IoV-wXNF6g1Wtg_sVC\u002Fview?usp=sharing) |\n | FILM | 7600 | 932 | 15009 | 5 | [film.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1s5K9Gb235-gO-IwevJLKAts7jExnnmrC\u002Fview?usp=sharing) |\n | BAT | 131 | 81 | 1038 | 4 | [bat.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1hRPtdFo9CzcxlFb84NWXg-HmViZnqshu\u002Fview?usp=sharing) |\n | EAT | 399 | 203 | 5994 | 4 | [eat.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1iE0AFKs1V5-nMk2XhV-TnfmPhvh0L9uo\u002Fview?usp=sharing) |\n | UAT | 1190 | 239 | 13599 | 4 | [uat.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1RUTHp54dVPB-VGPsEk8tV32DsSU0l-n_\u002Fview?usp=sharing) |\n\n**边数**：此处仅统计无向边的数量。\n\n2. 非图数据集\n\n | 数据集 | 样本数 | 维度 | 类型 | 类别数 | 链接 |\n | :-----: | :-----: | :-------: | :----: | :-----: | :----------------------------------------------------------: |\n | USPS | 9298 | 256 | 图像 | 10 | [usps.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F19oBkSeIluW3A5kcV7W0UM1Bt6V9Q62e-\u002Fview?usp=sharing) |\n | HHAR | 10299 | 561 | 记录 | 6 | [hhar.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F126OFuNhf2u-g9Tr0wukk0T8uM1cuPzy2\u002Fview?usp=sharing) |\n | REUT | 10000 | 2000 | 文本 | 4 | [reut.zip](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F12MpPWyN87bu-AQYTyjdEcofy1mgjgzi9\u002Fview?usp=sharing) |\n\n## 引用\n\n```\n\n@inproceedings{ITR,\n title={识别后再推荐：迈向无监督群体推荐},\n author={刘悦、朱世豪、杨天元、马健、钟文亮},\n booktitle={NeurIPS会议论文集},\n year={2024}\n}\n\n@article{ELCRec,\n title={面向推荐系统中意图学习的端到端可学习聚类},\n author={刘悦、朱世豪、夏俊、马英伟、马健、钟文亮、张冠楠、张克军、刘新旺},\n booktitle={国际神经信息处理系统会议论文集},\n year={2024}\n}\n\n@article{deep_graph_clustering_survey,\n title={深度图聚类综述：分类、挑战与应用},\n author={刘悦、夏俊、周思航、王思伟、郭锡峰、杨希洪、梁科、涂文轩、李Z·斯坦、刘新旺},\n journal={arXiv预印本 arXiv:2211.12875},\n year={2022}\n}\n\n@article{SCGC,\n title={简单对比图聚类},\n author={刘悦、杨希洪、周思航、刘新旺、王思伟、梁科、涂文轩、李亮},\n journal={IEEE神经网络与学习系统汇刊},\n year={2023},\n publisher={IEEE}\n}\n\n@inproceedings{Dink_Net,\n title={Dink-net：大规模图上的神经网络聚类},\n author={刘悦、梁科、夏俊、周思航、杨希洪、刘新旺、李Stan Z},\n booktitle={国际机器学习会议论文集},\n year={2023}\n}\n\n@inproceedings{TGC_ML_ICLR,\n title={深度时序图聚类},\n author={刘萌、刘悦、梁科、涂文轩、王思伟、周思航、刘新旺},\n booktitle={第12届国际表征学习大会},\n year={2024}\n}\n\n@inproceedings{HSAN,\n title={针对对比式深度图聚类的硬样本感知网络},\n author={刘悦、杨希洪、周思航、刘新旺、王振、梁科、涂文轩、李亮、段景灿、陈灿灿},\n booktitle={AAAI人工智能会议论文集},\n volume={37},\n number={7},\n pages={8914-8922},\n year={2023}\n}\n\n@inproceedings{DCRN,\n title={基于双重相关性降低的深度图聚类},\n author={刘悦、涂文轩、周思航、刘新旺、宋林轩、杨希洪、朱恩},\n booktitle={AAAI人工智能会议论文集},\n volume={36},\n number={7},\n pages={7603-7611},\n year={2022}\n}\n\n@inproceedings{liuyue_RGC,\n title={未知簇数的强化图聚类},\n author={刘悦、梁科、夏俊、杨希洪、周思航、刘萌、刘新旺、李Stan Z},\n booktitle={第31届ACM国际多媒体会议论文集},\n pages={3528--3537},\n year={2023}\n}\n\n@article{RGAE,\n title={重新思考用于属性图聚类的图自编码器模型},\n author={Mrabah, Nairouz、Bouguessa, Mohamed、Touati, Mohamed Fawzi、Ksantini, Riadh},\n journal={IEEE知识与数据工程汇刊},\n year={2022}\n}\n\n@article{yu2025guard,\n title = {G${}^2$uardFL：通过属性客户端图聚类保护联邦学习免受后门攻击},\n author = {于浩、马川、刘萌、杜天宇、丁明、向涛、季守玲、刘新旺},\n journal = {IEEE信息取证与安全汇刊},\n year = {2025},\n doi = {10.1109\u002FTIFS.2025.3639985}\n}\n```\n\n\n\n## 其他相关优秀仓库\n\n[深度属性图聚类统一框架](https:\u002F\u002Fgithub.com\u002FMarigoldwu\u002FA-Unified-Framework-for-Deep-Attribute-Graph-Clustering)\n\n[深度群体推荐优秀项目](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Group-Recommendation)\n\n[深度部分图机器学习优秀项目](https:\u002F\u002Fgithub.com\u002FWxTu\u002FAwesome-Partial-Graph-Machine-Learning)\n\n[深度知识图推理优秀项目](https:\u002F\u002Fgithub.com\u002FLIANGKE23\u002FAwesome-Knowledge-Graph-Reasoning)\n\n[深度时序图学习优秀项目](https:\u002F\u002Fgithub.com\u002FMGitHubL\u002FAwesome-Temporal-Graph-Learning)\n\n[深度多视图聚类优秀项目](https:\u002F\u002Fgithub.com\u002Fjinjiaqi1998\u002FAwesome-Deep-Multiview-Clustering)","# Awesome-Deep-Graph-Clustering 快速上手指南\n\n`Awesome-Deep-Graph-Clustering` (ADGC) 是一个汇集了最先进（SOTA）深度图聚类方法、论文代码及数据集的开源项目。本指南将帮助你快速搭建环境并运行相关代码。\n\n## 环境准备\n\n在开始之前，请确保你的开发环境满足以下要求：\n\n* **操作系统**: Linux (推荐 Ubuntu 18.04+), macOS 或 Windows (建议使用 WSL2)。\n* **Python 版本**: Python 3.8 或更高版本。\n* **硬件要求**: 建议配备 NVIDIA GPU 以加速模型训练（需安装 CUDA 和 cuDNN）。\n* **前置依赖**:\n * `git`: 用于克隆仓库。\n * `pip` 或 `conda`: 用于管理 Python 包。\n * `PyTorch`: 大多数深度学习图聚类算法基于 PyTorch 构建。\n\n## 安装步骤\n\n### 1. 克隆仓库\n首先，从 GitHub 克隆项目到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FAwesome-Deep-Graph-Clustering.git\ncd Awesome-Deep-Graph-Clustering\n```\n\n> **提示**：如果访问 GitHub 速度较慢，可使用国内镜像源加速：\n> ```bash\n> git clone https:\u002F\u002Fgitee.com\u002Fmirrors\u002FAwesome-Deep-Graph-Clustering.git\n> ```\n> *(注：若 Gitee 无同步镜像，建议使用 `git clone --depth=1` 减少下载量)*\n\n### 2. 创建虚拟环境\n推荐使用 Conda 创建独立的虚拟环境，避免依赖冲突：\n\n```bash\nconda create -n adgc python=3.9\nconda activate adgc\n```\n\n### 3. 安装依赖\n由于该仓库是论文和代码的集合，不同子项目（如 `RGC`, `LSEnet`, `SynC` 等）可能有独立的 `requirements.txt`。\n\n**通用依赖安装**（适用于大多数基于 PyTorch 的项目）：\n```bash\npip install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\npip install numpy scipy scikit-learn pandas matplotlib\npip install networkx torch-geometric\n```\n\n> **注意**：具体某个算法的详细依赖，请进入对应算法的子文件夹（例如 `cd RGC`），查看并安装其专属的 `requirements.txt`：\n> ```bash\n> pip install -r requirements.txt\n> ```\n\n## 基本使用\n\n该项目本身是一个资源列表，具体的使用方式取决于你选择的特定算法。以下以仓库中提供的 **RGC (Reinforcement Graph Clustering)** 为例，展示典型的运行流程。\n\n### 1. 准备数据\n大多数算法需要标准图数据集（如 Cora, Citeseer, Pubmed）。通常代码会自动下载，或需手动放入 `data\u002F` 目录。\n\n### 2. 运行示例\n进入具体算法目录并执行训练脚本。假设我们运行 RGC 算法：\n\n```bash\ncd RGC\npython main.py --dataset cora --epochs 200\n```\n\n典型参数说明：\n* `--dataset`: 指定数据集名称 (e.g., `cora`, `citeseer`)。\n* `--epochs`: 训练轮数。\n* `--lr`: 学习率。\n\n### 3. 查看结果\n运行结束后，终端通常会输出聚类性能指标（如 ACC, NMI, F1-score）。生成的模型文件和日志通常保存在 `results\u002F` 或 `checkpoints\u002F` 目录下。\n\n---\n**引用提示**：如果你在研究中使用了本仓库中的代码或处理后的数据集，请务必按照各子项目 README 中的要求引用相应的论文。","某生物信息学团队正试图从大规模蛋白质相互作用网络中识别功能未知的蛋白质群落，以加速新药靶点的发现。\n\n### 没有 Awesome-Deep-Graph-Clustering 时\n- **文献调研如大海捞针**：研究人员需在 arXiv、IEEE 等各大数据库手动筛选“深度图聚类”相关论文，耗时数周仍难以确认哪些是真正的 SOTA（最先进）方法。\n- **代码复现门槛极高**：找到的论文往往缺乏官方开源代码，或代码结构混乱、依赖缺失，导致算法复现失败率高达 80%，严重拖慢实验进度。\n- **数据预处理重复造轮子**：缺乏统一的基准数据集和标准化预处理脚本，团队成员需各自编写数据清洗代码，导致实验结果无法横向对比，可信度存疑。\n- **技术选型盲目试错**：由于缺乏对 LLM 结合图聚类等新兴架构的系统整理，团队容易错过前沿方案，只能沿用几年前的旧模型，挖掘精度遭遇瓶颈。\n\n### 使用 Awesome-Deep-Graph-Clustering 后\n- **一站式获取前沿成果**：直接查阅该仓库整理的分类列表，几分钟内即可锁定 2024 年最新的\"LLM 引导图聚类”等顶会论文，调研效率提升十倍。\n- **开箱即用的算法实现**：直接调用仓库中经过验证的 SOTA 方法代码，无需修复环境兼容性问题，将原本数周的复现周期缩短至几天。\n- **统一基准确保可比性**：利用仓库提供的标准数据集和预处理流程，团队能快速在不同算法间进行公平性能评估，显著提升了实验结论的说服力。\n- **精准把握技术风向**：通过清晰的架构分类（如新架构、综述文章），团队迅速引入适合生物网络特性的最新模型，成功将未知蛋白群的识别准确率提升了 15%。\n\nAwesome-Deep-Graph-Clustering 通过聚合高质量的论文、代码与数据，将科研人员从繁琐的基础设施搭建中解放出来，使其能专注于核心算法的创新与业务价值的挖掘。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyueliu1999_Awesome-Deep-Graph-Clustering_a7d95193.png","yueliu1999","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fyueliu1999_faf53813.jpg","Yue Liu a Ph.D. student at NUS.","National University of Singapore","Singapore","yueliu19990731@163.com",null,"yueliu1999.github.io","https:\u002F\u002Fgithub.com\u002Fyueliu1999",[82],{"name":83,"color":84,"percentage":85},"Python","#3572A5",100,1005,153,"2026-04-08T16:50:58","MIT","","未说明",{"notes":93,"python":91,"dependencies":94},"该仓库是一个深度图聚类（Deep Graph Clustering）相关论文和代码的集合列表（Awesome List），而非单一的独立软件工具。README 中列出了数十个不同的研究项目，每个项目都有独立的代码仓库链接和潜在的环境依赖。因此，无法从当前提供的文本中提取统一的操作系统、GPU、内存、Python 版本或依赖库要求。用户需根据具体想要运行的某篇论文的代码链接，前往其对应的子仓库查看具体的环境配置说明。",[],[14,16],[97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"deep-clustering","graph-neural-networks","self-supervised-learning","representation-learning","surveys","data-mining","deep-learning","graph-convolutional-networks","graph-embedding","network-embedding","gcn","machine-learning","clustering","data-mining-algorithms","graphclustering","2026-03-27T02:49:30.150509","2026-04-09T09:33:23.635584",[],[]]