[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-FanzhenLiu--Awesome-Deep-Community-Detection":3,"tool-FanzhenLiu--Awesome-Deep-Community-Detection":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",144730,2,"2026-04-07T23:26:32",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107888,"2026-04-06T11:32:50",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":10,"last_commit_at":59,"category_tags":60,"status":17},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[35,15,13,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":78,"owner_website":79,"owner_url":80,"languages":78,"stars":81,"forks":82,"last_commit_at":83,"license":84,"difficulty_score":85,"env_os":86,"env_gpu":87,"env_ram":87,"env_deps":88,"category_tags":91,"github_topics":92,"view_count":32,"oss_zip_url":78,"oss_zip_packed_at":78,"status":17,"created_at":105,"updated_at":106,"faqs":107,"releases":108},5265,"FanzhenLiu\u002FAwesome-Deep-Community-Detection","Awesome-Deep-Community-Detection","Deep and conventional community detection related papers, implementations, datasets, and tools.","Awesome-Deep-Community-Detection 是一个专注于社区检测领域的开源资源合集，旨在为研究者提供从传统统计模型到前沿深度学习方法的全面指引。在社交网络、生物信息学等复杂网络分析中，如何精准识别紧密连接的节点群体（即“社区”）一直是个核心难题，尤其是面对大规模动态数据时，传统算法往往力不从心。\n\n该项目系统性地整理了相关的学术论文、代码实现、基准数据集及实用工具。其独特亮点在于清晰的分类体系：不仅涵盖了基于卷积神经网络（GCN）、图注意力网络（GAT）、生成对抗网络（GAN）及自编码器等多种深度学习架构的最新成果，还保留了经典的非深度学习方法作为对比参考。此外，项目收录了多篇权威综述文章和技术发展时间线，帮助用户快速把握领域脉络。\n\nAwesome-Deep-Community-Detection 特别适合人工智能研究人员、数据科学家以及从事图神经网络开发的工程师使用。无论是希望复现最新算法、寻找合适的实验数据集，还是想要深入了解社区检测技术的演进历程，这里都能提供一站式的高质量资源支持，是进入该研究领域不可或缺的入门指南与案头手册。","# Awesome Deep Community Detection\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) [![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=flat-square)](http:\u002F\u002Fmakeapullrequest.com) ![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFanzhenLiu\u002Fawesome-deep-community-detection?color=yellow&label=Stars) ![GitHub forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFanzhenLiu\u002Fawesome-deep-community-detection?color=blue&label=Forks) \n\nA collection of papers, implementations, datasets, and tools for deep and non-deep community detection.\n\n- [Awesome Deep Community Detection](#awesome-Deep-Community-Detection)\n  - [Survey](#survey)\n  - [Convolutional Networks-based Community Detection](#convolutional-networks-based-community-detection)\n  \t- [CNN-based Community Detection](#cnn-based-community-detection)\n  \t- [GCN-based Community Detection](#gcn-based-community-detection)\n  - [Graph Attention Network-based Community Detection](#graph-attention-network-based-community-detection)\n  - [Generative Adversarial Network-based Community Detection](#graph-adversarial-network-based-community-detection)\n  - [Autoencoder-based Community Detection](#autoencoder-based-community-detection)\n  - [Other Deep Learning-based Community Detection](#other-deep-learning-based-community-detection)\n  - [Non-Deep Learning-based Community Detection](#non-deep-learning-based-communtiy-detection)\n  - [Datasets](#datasets)\n  - [Tools](#tools)  \n\n----------\n## Traditional Methods _VS._ Deep Learninig-based Methods\n![taxonomy](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFanzhenLiu_Awesome-Deep-Community-Detection_readme_bf2a11b422a3.png)\n\n----------\n## A Timeline of Community Detection Development\n![timeline](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFanzhenLiu_Awesome-Deep-Community-Detection_readme_be85ba9ed5b9.png)\n\n----------\n## Survey\n| Paper Title | Venue | Year | Materials | \n| ---- | :----: | :----: | :----: | \n| A comprehensive survey on community detection with deep learning | IEEE TNNLS | 2022 | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9732192)] \u003Cbr> [[Report](https:\u002F\u002Fwww.aminer.cn\u002Fresearch_report\u002F60da8c5f30e4d5752f50e7af)] \u003Cbr> [[Supplementary](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F359222598_Supplementary_DeepCommunityDetectionSurveypdf)]|\n| A survey of community detection approaches: From statistical modeling to deep learning | IEEE TKDE | 2021 | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9511798)]|\n| Deep learning for community detection: Progress, challenges and opportunities | IJCAI | 2020 | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0693.pdf)] \u003Cbr>[[Report](https:\u002F\u002Fcloud.tencent.com\u002Fdeveloper\u002Farticle\u002F1632305)]| \n| A survey of community detection methods in multilayer networks | Data Min. Knowl. Discov. | 2020 | [[Paper](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10618-020-00716-6)] |\n| Community detection in node-attributed social networks: A survey | Comput. Sci. Rev. | 2020 | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1574013720303865)] |\n| Community detection in networks: A multidisciplinary review | J. Netw. Comput. Appl. | 2018| [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1084804518300560)] |\n| Community discovery in dynamic networks: A survey | ACM Comput. Surv. | 2018 | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3172867)] |\n| Evolutionary computation for community detection in networks: A review | IEEE TEVC | 2018 | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8004509)] |\n| Metrics for community analysis: A survey | ACM Comput. Surv. | 2017 | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3091106)] |\n| Network community detection: A review and visual survey | Preprint | 2017 | [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.00977)] |\n| Community detection in networks: A user guide | Phys. Rep. | 2016 | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0370157316302964)] |\n| Community detection in social networks | WIREs Data Min. Knowl. Discov. | 2016 | [[Paper](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fwidm.1178)]|\n| Overlapping community detection in networks: The state-of-the-art and comparative study| ACM Comput. Surv. | 2013 | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F2501654.2501657)] |\n| Clustering and community detection in directed networks: A survey | Phys. Rep. | 2013 | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0370157313002822)] |\n| Community detection in graphs | Phys. Rep. | 2010 | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0370157309002841)] |\n\n----------\n## Convolutional Networks-based Community Detection\n### CNN-based Community Detection\n| Paper Title | Venue | Year | Method | Materials | \n| ---- | :----: | :----: | :----: | :----: | \n|Inductive representation learning via CNN for partially-unseen attributed networks | IEEE TNSE | 2021 | IEPAN | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9314087)] |\n|A deep learning approach for semi-supervised community detection in online social networks | Knowl.-Based Syst. | 2021 | SparseConv2D | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0950705121006079)] |\n|Edge classification based on convolutional neural networks for community detection in complex network | Physica A | 2020 | ComNet-R | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0378437120304271)] |\n|A deep learning based community detection approach | SAC | 2019 | SparseConv | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3297280.3297574)] |\n|Deep community detection in topologically incomplete networks | Physica A | 2017 | Xin _et al._ | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0378437116308342)] |\n\n### GCN-based Community Detection \n| Paper Title | Venue | Year | Method | Materials | \n| ---- | :----: | :----: | :----: | :----: | \n|Complex exponential graph convolutional networks | Inf. Sci. | 2023 | CEGCN | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2023.119041)] [[Code](https:\u002F\u002Fgithub.com\u002FDaffominga\u002Fcegcn)] |\n|Community detection based on community perspective and graph convolutional network| Expert Syst. Appl. | 2023 | CPGC | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417423012502)] |\n|Heterogeneous question answering community detection based on graph neural network | Inf. Sci. | 2023 | HCDBG | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2022.10.126)] |\n|Overlapping community detection on complex networks with graph convolutional networks | Comput. Commun. | 2023 | CDMG | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.comcom.2022.12.008)] |\n|Deep MinCut: Learning node embeddings from detecting communities | Pattern Recognit. | 2022 | DMC | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2022.109126)] |\n|End-to-end modularity-based community co-partition in bipartite networks| CIKM | 2022 | BiCoN+GCN | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3511808.3557309)] |\n|CLARE: A semi-supervised community detection algorithm | KDD | 2022 | CLARE | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3534678.3539370)] [[Code](https:\u002F\u002Fgithub.com\u002FFDUDSDE\u002FKDD2022CLARE)] |\n|Efficient graph convolution for joint node representation learning and clustering  | WSDM | 2022 | GCC | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3488560.3498533)] [[Code](https:\u002F\u002Fgithub.com\u002Fchakib401\u002Fgraph_convolutional_clustering)] |\n|Geometric graph representation learning via maximizing rate reduction | WWW | 2022 | $G^2R$ | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3485447.3512170)] [[Code](https:\u002F\u002Fgithub.com\u002Fahxt\u002FG2R)] | \n| RepBin: Constraint-based graph representation learning for metagenomic binning | AAAI | 2022 | RepBin | [[Paper](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-4979.XueH.pdf)] [[Code](https:\u002F\u002Fgithub.com\u002Fxuehansheng\u002FRepBin)] |\n|SSSNET: Semi-supervised signed network clustering | SDM | 2022 | SSSNET | [[Paper](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2110.06623.pdf)] [[Code](https:\u002F\u002Fgithub.com\u002FSherylHYX\u002FSSSNET_Signed_Clustering)] | \n|Learning Guarantees for Graph Convolutional Networks on The Stochastic Block Model | ICLR | 2022 | GCN-SBM | [[Paper](https:\u002F\u002Fopenreview.net\u002Fforum?id=dpXL6lz4mOQ)] |\n|When convolutional network meets temporal heterogeneous graphs: An effective community detection method | IEEE TKDE| 2021 | THGCN | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9479741)] |\n|Multi-view contrastive graph clustering | NIPS | 2021 | MCGC | [[paper](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002F10c66082c124f8afe3df4886f5e516e0-Paper.pdf)] [[Code](https:\u002F\u002Fgithub.com\u002FPanern\u002FMCGC)] |\n|Graph debiased contrastive learning with joint representation clustering | IJCAI | 2021 | Zhao _et al._ | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0473.pdf)] | \n|Spectral embedding network for attributed graph clustering | Neural Netw. | 2021 | SENet | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0893608021002227)] | \n|Unsupervised learning for community detection in attributed networks based on graph convolutional network | Neurocomputing | 2021 | SGCN | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0925231221008110)] |\n|Adaptive graph encoder for attributed graph embedding | KDD | 2020 | AGE | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403140)][[Code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FAGE)] |\n|CommDGI: Community detection oriented deep graph infomax | CIKM | 2020 | CommDGI | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412042)] | \n|Going deep: Graph convolutional ladder-shape networks | AAAI | 2020 | GCLN | [[Paper](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5673\u002F5529)] |\n|Independence promoted graph disentangled networks | AAAI | 2020 | IPGDN | [[Paper](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5929\u002F5785)] |\n|Supervised community detection with line graph neural networks | ICLR | 2019 | LGNN | [[Paper](https:\u002F\u002Fopenreview.net\u002Fpdf?id=H1g0Z3A9Fm)][[Code](https:\u002F\u002Fgithub.com\u002Fzhengdao-chen\u002FGNN4CD)] |\n|Graph convolutional networks meet Markov random fields: Semi-supervised community detection in attribute networks | AAAI | 2019 | MRFasGCN | [[Paper](https:\u002F\u002Fwww.aaai.org\u002Fojs\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3780\u002F3658)] |\n|Overlapping community detection with graph neural networks | DLG Workshop, KDD | 2019 | NOCD | [[Paper](https:\u002F\u002Fdeep-learning-graphs.bitbucket.io\u002Fdlg-kdd19\u002Faccepted_papers\u002FDLG_2019_paper_3.pdf)][[Code](https:\u002F\u002Fgithub.com\u002Fshchur\u002Foverlapping-community-detection)] |\n|Attributed graph clustering via adaptive graph convolution | IJCAI | 2019 | AGC | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0601.pdf)][[Code](https:\u002F\u002Fgithub.com\u002Fkarenlatong\u002FAGC-master)] |\n|CayleyNets: Graph convolutional neural networks with complex rational spectral filters | IEEE TSP | 2019 | CayleyNets | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8521593)][[Code](https:\u002F\u002Fgithub.com\u002Famoliu\u002FCayleyNet)] |\n\n----------\n## Graph Attention Network-based Community Detection\n| Paper Title | Venue | Year | Method | Materials | \n| ---- | :----: | :----: | :----: | :----: | \n|CSAT: Contrastive sampling-aggregating transformer for community detection in attribute-missing networks | IEEE TCSS | 2023 | CSAT | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10210121)] |\n|A graph-enhanced attention model for community detection in multiplex networks | Expert Syst. Appl. | 2023 | GEAM | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417423010540)][[Code](https:\u002F\u002Fgithub.com\u002FHustMinsLab\u002FGEAM)] |\n|Hierarchical attention network for attributed community detection of joint representation | Neural Comput. Appl. | 2022 | HiAN | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs00521-021-06723-y)] |\n|Detecting communities from heterogeneous graphs: A context path-based graph neural network model | CIKM | 2021 | \u003Cnobr> CP-GNN \u003Cnobr> | [[Paper](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.02058.pdf)][[Code](https:\u002F\u002Fgithub.com\u002FRManLuo\u002FCP-GNN)] | \n|HDMI: High-order deep multiplex infomax | WWW | 2021 | HDMI | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002FfullHtml\u002F10.1145\u002F3442381.3449971)][[Code](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FHDMI)] |\n|Self-supervised heterogeneous graph neural network with co-contrastive learning | KDD | 2021 | HeCo | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467415)][[Code](https:\u002F\u002Fgithub.com\u002Fliun-online\u002FHeCo)] |\n|Unsupervised attributed multiplex network embedding | AAAI | 2020 | DMGI | [[Paper](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5985)][[Code](https:\u002F\u002Fgithub.com\u002Fpcy1302\u002FDMGI)] |\n|MAGNN: Metapath aggregated graph neural network for heterogeneous graph embedding | WWW | 2020 | MAGNN | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380297)] [[Code](https:\u002F\u002Fgithub.com\u002Fcynricfu\u002FMAGNN)] |\n\n----------\n## Graph Adversarial Network-based Community Detection\n| Paper Title | Venue | Year | Method | Materials | \n| ---- | :----: | :----: | :----: | :----: |  \n|CANE: Community-aware network embedding via adversarial training |Knowl. Inf. Syst. | 2021 | CANE | [[Paper](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007%2Fs10115-020-01521-9)] | \n|Self-training enhanced: Network embedding and overlapping community detection with adversarial learning | IEEE TNNLS | 2021 | ACNE \u003Cbr> ACNE-ST \u003Cbr> | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9451542)] |\n|Adversarial Learning of Balanced Triangles for Accurate Community Detection on Signed Networks |ICDM | 2021 | ABC | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9679159)] | \n|SEAL: Learning heuristics for community detection with generative adversarial networks | KDD | 2020 | SEAL | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3394486.3403154)][[Code](https:\u002F\u002Fgithub.com\u002Fyzhang1918\u002Fkdd2020seal)] |\n|Multi-class imbalanced graph convolutional network learning | IJCAI | 2020 | DR-GCN | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0398.pdf)] |\n|JANE: Jointly adversarial network embedding | IJCAI | 2020| JANE | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0192.pdf)] |\n|ProGAN: Network embedding via proximity generative adversarial network | KDD | 2019 | ProGAN | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3292500.3330866)] |\n|CommunityGAN: Community detection with generative adversarial nets | WWW | 2019 | CommunityGAN | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3308558.3313564)][[Code](https:\u002F\u002Fgithub.com\u002FSamJia\u002FCommunityGAN)] |\n\n----------\n## Autoencoder-based Community Detection\n| Paper Title | Venue | Year | Method | Materials | \n| ---- | :----: | :----: | :----: | :----: |\n|A graph convolutional fusion model for community detection in multiplex networks | Data Min. Knowl. Discov. | 2023 | GCFM | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10618-023-00932-w)] |\n|A novel network core structure extraction algorithm utilized variational autoencoder for community detection | Expert Syst. Appl. | 2023 | CSEA | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eswa.2023.119775)][[Code](https:\u002F\u002Fgithub.com\u002FPeterWana\u002FCSEA)] |\n|Community detection based on unsupervised attributed network embedding | Expert Syst. Appl. | 2023 | CDBNE | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eswa.2022.118937)][[Code](https:\u002F\u002Fgithub.com\u002Fxidizxc\u002FCDBNE)] |\n|Exploring temporal community structure via network embedding | IEEE TCYB | 2022 | VGRGMM | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9768181)]|\n|Graph community infomax | ACM TKDD | 2022 | GCI | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3480244)] |\n|Multi-modal non-Euclidean brain network analysis with community detection and convolutional autoencoder | IEEE TETCI | 2022 | M2CDCA | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9773106)] |\n|Deep neighbor-aware embedding for node clustering in attributed graphs | Pattern Recognit. | 2022 | DNENC | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2021.108230)] |\n|Semi-supervised overlapping community detection in attributed graph with graph convolutional autoencoder | Inf. Sci. | 2022 | SSGCAE | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2022.07.036)] |\n|A weighted network community detection algorithm based on deep learning | Appl. Math. Comput. | 2021 | WCD | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0096300321000606)] |\n| DNC: A deep neural network-based clustering-oriented network embedding algorithm | J. Netw. Comput. Appl. | 2021 | DNC | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1084804520303209)] |\n|Boosting nonnegative matrix factorization based community detection with graph attention auto-encoder | IEEE TBD | 2021 | NMFGAAE | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9512416)]|\n|Self-supervised graph convolutional network for multi-view clustering | IEEE TMM | 2021 | SGCMC | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9472979)] |\n|Graph embedding clustering: Graph attention auto-encoder with cluster-specificity distribution | Neural Netw. | 2021 | GEC-CSD | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0893608021002008)][[Code](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FSGCMC)] |\n|An evolutionary autoencoder for dynamic community detection | Sci. China Inf. Sci. | 2020 | \u003Cnobr> sE-Autoencoder \u003Cnobr> | [[Paper](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11432-020-2827-9)] |\n|Stacked autoencoder-based community detection method via an ensemble clustering framework | Inf. Sci. | 2020 | CDMEC | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS002002552030270X)] |\n|Community-centric graph convolutional network for unsupervised community detection | IJCAI | 2020 | GUCD | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0486.pdf)] |\n|Structural deep clustering network |  WWW | 2020 | SDCN | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3366423.3380214)][[Code](https:\u002F\u002Fgithub.com\u002Fbdy9527\u002FSDCN)] |\n|One2Multi graph autoencoder for multi-view graph clustering | WWW | 2020 | One2Multi | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3366423.3380079)][[Code](https:\u002F\u002Fgithub.com\u002Fgooglebaba\u002FWWW2020-O2MAC)] |\n|Multi-view attribute graph convolution networks for clustering | IJCAI | 2020 | MAGCN | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0411.pdf)] |\n|Deep multi-graph clustering via attentive cross-graph association | WSDM | 2020 | DMGC | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3336191.3371806)][[Code](https:\u002F\u002Fgithub.com\u002Fflyingdoog\u002FDMGC)] |\n|Effective decoding in graph auto-encoder using triadic closure | AAAI | 2020 | TGA \u003Cbr> TVGA \u003Cbr> | [[Paper](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5437\u002F5293)] |\n|Graph representation learning via ladder gamma variational autoencoders | AAAI | 2020 | LGVG | [[Paper](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6013\u002F5869)] |\n|High-performance community detection in social networks using a deep transitive autoencoder | Inf. Sci. | 2019 | \u003Cnobr> Transfer-CDDTA \u003Cnobr> | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0020025519303251)] |\n|Attributed graph clustering: A deep attentional embedding approach | IJCAI | 2019 | DAEGC | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0509.pdf)] |\n|Stochastic blockmodels meet graph neural networks | ICML | 2019 | DGLFRM | [[Paper](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fmehta19a\u002Fmehta19a.pdf)][[Code](https:\u002F\u002Fgithub.com\u002Fnikhil-dce\u002FSBM-meet-GNN)] |\n|Variational graph embedding and clustering with laplacian eigenmaps | IJCAI | 2019 | VGECLE | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0297.pdf)] |\n|Optimizing variational graph autoencoder for community detection | BigData | 2019 | VGAECD-OPT | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9006123)] |\n|Integrative network embedding via deep joint reconstruction | IJCAI | 2018 | UWMNE | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F0473.pdf)] |\n|Deep attributed network embedding | IJCAI | 2018 | DANE | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F0467.pdf)][[Code](https:\u002F\u002Fgithub.com\u002Fgaoghc\u002FDANE)] |\n|Deep network embedding for graph representation learning in signed networks | IEEE TCYB | 2018 | DNE-SBP | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8486671)][[Code](https:\u002F\u002Fgithub.com\u002Fshenxiaocam\u002FDeep-network-embedding-for-graph-representation-learning-in-signed-networks)] |\n|DFuzzy: A deep learning-based fuzzy clustering model for large graphs | Knowl. Inf.  Syst. | 2018 | DFuzzy | [[Paper](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10115-018-1156-3)] |\n|Learning community structure with variational autoencoder | ICDM | 2018 | VGAECD | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8594831)] |\n|Adversarially regularized graph autoencoder for graph embedding | IJCAI | 2018 | ARGA \u003Cbr> ARVGA \u003Cbr> | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F0362.pdf)][[Code](https:\u002F\u002Fgithub.com\u002FRuiqi-Hu\u002FARGA)]| \n|BL-MNE: Emerging heterogeneous social network embedding through broad learning with aligned autoencoder | ICDM | 2017 | DIME | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1109\u002FICDM.2017.70)][[Code](http:\u002F\u002Fwww.ifmlab.org\u002Ffiles\u002Fcode\u002FAligned-Autoencoder.zip)] |\n|MGAE: Marginalized graph autoencoder for graph clustering | CIKM | 2017 | MGAE | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3132847.3132967)][[Code](https:\u002F\u002Fgithub.com\u002FFakeTibbers\u002FMGAE)] |\n|Graph clustering with dynamic embedding | Preprint | 2017 | GRACE | [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.08249)] | \n|Modularity based community detection with deep learning | IJCAI | 2016 | semi-DRN | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F16\u002FPapers\u002F321.pdf)][[Code](http:\u002F\u002Fyangliang.github.io\u002Fcode\u002FDC.zip)] |\n|Deep neural networks for learning graph representations | AAAI | 2016 | DNGR | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.5555\u002F3015812.3015982)] |\n|Learning deep representations for graph clustering | AAAI | 2014 | GraphEncoder | [[Paper](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI14\u002Fpaper\u002Fview\u002F8527\u002F8571)][[Code](https:\u002F\u002Fgithub.com\u002Fquinngroup\u002Fdeep-representations-clustering)] |\n\n----------\n## Other Deep Learning-based Community Detection \n| Paper Title | Venue | Year | Method | Materials | \n| ---- | :----: | :----: | :----: | :----: | \n| Contrastive deep nonnegative matrix factorization for community detection | ICASSP | 2024 | CDNMF | [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.02357)][[Code](https:\u002F\u002Fgithub.com\u002F6lyc\u002FCDNMF)] |\n|A hyperbolic approach for learning communities on graphs | Data Min. Knowl. Discov. | 2023 | RComE | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10618-022-00902-8)][[Code](https:\u002F\u002Fwww.github.com\u002Ftgeral68\u002FHyperbolicGraphAndGMM)] |\n|Deep alternating non-negative matrix factorisation | Knowl.-Based Syst. | 2022 |  DA-NMF | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.109210)] |\n|CGC: Contrastive Graph Clustering for Community Detection and Tracking | WWW | 2022 | CGC | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3485447.3512160)] |\n|Deep graph clustering via dual correlation reduction | AAAI | 2022 | DCRN | [[Paper](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-5928.LiuY.pdf)] [[Code](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FDCRN)] |\n|Cluster-aware heterogeneous information network embedding | WSDM | 2022 | VaCA-HINE | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498385)] |\n|Graph filter-based multi-view attributed graph clustering | IJCAI | 2021 | MvAGC | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0375.pdf)] [[Code](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FMvAGC)] |\n|A deep learning framework for self-evolving hierarchical community detection | CIKM | 2021 | ReinCom | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3459637.3482223)] |\n|Unsupervised learning of joint embeddings for node representation and community detection | ECML-PKDD | 2021 | J-ENC | [[Paper](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-86520-7_2)] |\n|Community detection based on modularized deep nonnegative matrix factorization | Int. J. Pattern Recognit. Artif. Intell. | 2020 | MDNMF | [[Paper](https:\u002F\u002Fwww.worldscientific.com\u002Fdoi\u002Fabs\u002F10.1142\u002FS0218001421590060)] |\n|Deep autoencoder-like nonnegative matrix factorization for community detection | CIKM | 2018 | DANMF | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3269206.3271697)][[Code](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002FDANMF)] |\n|Community discovery in networks with deep sparse filtering | Pattern Recognit. | 2018 | DSFCD | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS003132031830116X)] |\n|A non-negative symmetric encoder-decoder approach for community detection | CIKM | 2017 | Sun _et al._ | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3132847.3132902)] |\n\n----------\n## Non-Deep Learning-based Communtiy Detection\n| Paper Title | Venue | Year | Method | Materials |\n| ---- | :----: | :----: | :----: | :----: |\n| CataBEEM: Integrating latent interaction categories in node-wise community detection models for network data | ICML | 2023 | CataBEEM | [[Paper](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fzhang23h.html)][[Code](https:\u002F\u002Fgithub.com\u002FYuhuaZhang1995\u002FCataBEEM)] |\n|Nonnegative matrix factorization based on node centrality for community detection | ACM TKDD | 2023 | NCNMF | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Ffull\u002F10.1145\u002F3578520)][[Code](https:\u002F\u002Fgithub.com\u002FwowoHead\u002FNCNMF)] |\n|Dual structural consistency preserving community detection on social networks | IEEE TKDE | 2023 | DSCPCD | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1109\u002FTKDE.2022.3230502)][[Code](https:\u002F\u002Fgithub.com\u002Fwyy-cs\u002FDSCPCD)] |\n|Symmetry and graph bi-regularized non-negative matrix factorization for precise community detection | IEEE TASAE | 2023 | B-NMF | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1109\u002FTASE.2023.3240335)]|\n|Multi-view metro station clustering based on passenger flows: A functional data-edged network community detection approach | Data Min. Knowl. Discov. | 2023 | F\u003Csup>2\u003C\u002Fsup>MVNCD | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10618-023-00916-w)] |\n|Multiplex network community detection algorithm based on motif awareness | Knowl.-Based Syst. | 2023| CDMA | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.110136)] |\n|Community detection via autoencoder-like nonnegative tensor decomposition | IEEE TNNLS | 2022 | ANTD | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9904739)] |\n|Graph regularized nonnegative matrix factorization for community detection in attributed networks| IEEE TNSE | 2022 | AGNMF-AN | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9904900)]\n|Modeling and detecting communities in node attributed networks | IEEE TKDE | 2022 | CRSBM | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9852668)] |\n|The trade-off between topology and content in community detection: An adaptive encoder-decoder-based NMF approach | Expert Syst. Appl. | 2022 | ANMF | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eswa.2022.118230)] |\n|Community detection in subspace of attribute | Inf. Sci. | 2022 | SOA | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2022.04.047)] |\n|Explainability in graph data science: Interpretability, replicability, and reproducibility of community detection | IEEE Signal Process. Mag. | 2022 | --| [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9810084)] |\n|Differentially private community detection for stochastic block models | ICML | 2022 | Seif _et al._ | [[Paper](http:\u002F\u002F128.84.4.18\u002Fabs\u002F2202.00636)] |\n|Community detection in multiplex networks based on evolutionary multi-task optimization and evolutionary clustering ensemble | IEEE TEVC | 2022 | BSMCD | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9802693)] |\n|Fine-grained attributed graph clustering | SDM | 2022 | FGC | [[Paper](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977172.42)] [[Code](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FFGC)] |\n|HB-DSBM: Modeling the dynamic complex networks from community level to node level | IEEE TNNLS | 2022 | HB-DSBM | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9721420)]|\n|PMCDM: Privacy-preserving multiresolution community detection in multiplex networks | Knowl.-Based Syst. | 2022 | PMCDM | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.108542)] |\n|Rearranging 'indivisible' blocks for community detection | IEEE TKDE | 2022 | RaidB | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9771068)] |\n|Information diffusion-aware likelihood maximization optimization for community detection | Inf. Sci. | 2022 | EM-CD \u003Cbr> L-Louvain \u003Cbr> | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0020025522003334)] |\n|Community detection in partially observable social networks | ACM TKDD | 2022 | KroMFac | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3461339)] |\n|Diverse and experienced group discovery via hypergraph clustering | SDM | 2022 | Amburg _et al._ | [[Paper](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977172.17)] [[Code](https:\u002F\u002Fgithub.com\u002Filyaamburg\u002Ffair-clustering-for-diverse-and-experienced-groups)] |\n|Community detection in graph: An embedding method | IEEE TNSE | 2022 | SENMF | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9626627)] | \n|Community detection using local group assimilation | Expert Syst. Appl. | 2022| LGA | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417422010600)] |\n|Identifying Early Warning Signals from News Using Network Community Detection | AAAI | 2022| Le Vine _et al._ | [[Paper](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F21503\u002F21252)] |\n|Residual2Vec: Debiasing graph embedding with random graphs | NIPS | 2021 | residual2vec | [[Paper](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002Fca9541826e97c4530b07dda2eba0e013-Paper.pdf)] [[Code](https:\u002F\u002Fgithub.com\u002Fskojaku\u002Fresidual2vec)] |\n|Streaming belief propagation for community detection | NIPS | 2021 | StSBM | [[Paper](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002Fe2a2dcc36a08a345332c751b2f2e476c-Paper.pdf)] |\n|Triangle-aware spectral sparsifiers and community detection | KDD | 2021 | Sotiropoulos _et al._ | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467260)] [[Code](https:\u002F\u002Fwww.dropbox.com\u002Fs\u002F0p0ybkpx19jt3ii\u002FcodeKDDTriangleAware.zip?dl=0)] |\n|Self-guided community detection on networks with missing edges | IJCAI | 2021 | SGCD | [[Paper](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0483.pdf)] |\n|Effective and scalable clustering on massive attributed graphs | WWW | 2021 | ACMin | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3442381.3449875)] [[Code](https:\u002F\u002Fgithub.com\u002FAnryYang\u002FACMin)] |\n|Scalable Community Detection via Parallel Correlation Clustering | VLDB | 2021 | Shi _et al._ | [[Paper](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp2305-shi.pdf)] [[Code](https:\u002F\u002Fgithub.com\u002Fjeshi96\u002Fparallel-correlation-clustering)] |\n|Proximity-based group formation game model for community detection in social network | Knowl.-Based Syst. | 2021 | PBCD | [[Paper](https:\u002F\u002Flinkinghub.elsevier.com\u002Fretrieve\u002Fpii\u002FS0950705120307991)] |\n|When random initializations help: A study of variational inference for community detection | J. Mach. Learn. Res. | 2021 | BCAVI | [[Paper](https:\u002F\u002Fwww.jmlr.org\u002Fpapers\u002Fvolume22\u002F19-630\u002F19-630.pdf)] |\n|Compactness preserving community computation via a network generative process | IEEE TETCI | 2021 | FCOCD | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9548676)] |\n|Identification of communities with multi-semantics via bayesian generative model | IEEE TBD | 2021 | ICMS | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9632396)] |\n|A network embedding-enhanced Bayesian model for generalized community detection in complex networks | Inf. Sci. | 2021 | NEGCD | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2021.06.020)] |\n|Multi-objective evolutionary clustering for large-scale dynamic community detection | Inf. Sci. | 2021 | \u003Cnobr> DYN-MODPSO \u003Cnobr> | [[Paper](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0020025520311117)] |\n|A joint community detection model: Integrating directed and undirected probabilistic graphical models via factor graph with attention mechanism | IEEE TBD | 2021 | AdaMRF | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9511816)] |\n|SimClusters: Community-based representations for heterogeneous recommendations at Twitter | KDD | 2020 | SimClusters | [[Paper](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403370)] [[Code](https:\u002F\u002Fgithub.com\u002Ftwitter\u002Fsbf)] | \n|Evolutionary markov dynamics for network community detection | IEEE TKDE | 2020 | ePMCL | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9099469)] |\n|A network reduction-based multiobjective evolutionary algorithm for community detection in large-scale complex networks | IEEE TCYB | 2020 | RMOEA | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8486719)] |\n|Integrating group homophily and individual personality of topics can better model network communities | ICDM | 2020 | GHIPT | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9338379)] |\n|Community preserving network embedding based on memetic algorithm | IEEE TETCI | 2020 | MemeRep | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8449095)] |\n|Detecting the evolving community structure in dynamic social networks | World Wide Web J. | 2020 | DECS | [[Paper](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11280-019-00710-z)] [[Code](https:\u002F\u002Fgithub.com\u002FFanzhenLiu\u002FDECS)] |\n|EdMot: An edge enhancement approach for motif-aware community detection | KDD | 2019 | EdMot | [[Paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330882)] |\n|LPANNI: Overlapping community detection using label propagation in large-scale complex networks | IEEE TKDE | 2019 | LPANNI | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8443129)] |\n|Detecting prosumer-community groups in smart grids from the multiagent perspective | IEEE TSMC | 2019 | PVMAS | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8660684)] |\n|Local community mining on distributed and dynamic networks from a multiagent perspective | IEEE TCYB | 2016 | AOCCM | [[Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7124425)] |\n|General optimization technique for high-quality community detection in complex networks | Phys. Rev. E | 2014 | Combo | [[Paper](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.90.012811)] |\n|Spectral methods for community detection and graph partitioning | Phys. Rev. E | 2013 | -- | [[Paper](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.88.042822)] |\n|Stochastic blockmodels and community structure in networks | Phys. Rev. E | 2011 | DCSBM | [[Paper](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.83.016107)] |\n\n----------\n## Datasets\n### Citation\u002FCo-authorship Networks\n- Citeseer, Cora, Pubmed https:\u002F\u002Flinqs.soe.ucsc.edu\u002Fdata\n- DBLP http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fcom-DBLP.html\n- Chemistry, Computer Science, Medicine, Engineering http:\u002F\u002Fkddcup2016.azurewebsites.net\u002F\n### Online Social Networks\n- Facebook http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fego-Facebook.html\n- Epinions http:\u002F\u002Fwww.epinions.com\u002F\n- Youtube http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fcom-Youtube.html\n- Last.fm https:\u002F\u002Fwww.last.fm\u002F\n- LiveJournal http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fsoc-LiveJournal1.html\n- Gplus http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fego-Gplus.html\n### Traditional Social Networks\n- Cellphone Calls http:\u002F\u002Fwww.cs.umd.edu\u002Fhcil\u002FVASTchallenge08\u002F\n- Enron Mail http:\u002F\u002Fwww.cs.cmu.edu\u002F~enron\u002F\n- Friendship https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F2501654.2501657\n- Rados http:\u002F\u002Fnetworkrepository.com\u002Fia-radoslaw-email.php \n- Karate, Football, Dolphin http:\u002F\u002Fwww-personal.umich.edu\u002F~mejn\u002Fnetdata\u002F\n### Webpage Networks\n- IMDb https:\u002F\u002Fwww.imdb.com\u002F\n- Wiki https:\u002F\u002Flinqs.soe.ucsc.edu\u002Fdata\n### Product Co-purchasing Networks\n- Amazon http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002F#amazon\n### Other Networks\n- Internet http:\u002F\u002Fwww-personal.umich.edu\u002F~mejn\u002Fnetdata\u002F\n- Java https:\u002F\u002Fgithub.com\u002Fgephi\u002Fgephi\u002Fwiki\u002FDatasets\n- Hypertext http:\u002F\u002Fwww.sociopatterns.org\u002Fdatasets\n \n ----------\n## Tools\n- Gephi https:\u002F\u002Fgephi.org\u002F\n- Pajek http:\u002F\u002Fmrvar.fdv.uni-lj.si\u002Fpajek\u002F\n- LFR https:\u002F\u002Fwww.santofortunato.net\u002Fresources\n\n----------\n**Disclaimer**\n\nIf you have any questions, please feel free to contact us.\nEmails: \u003Cu>fanzhen.liu@hdr.mq.edu.au\u003C\u002Fu>, \u003Cu>xing.su2@hdr.mq.edu.au\u003C\u002Fu>\n","# 令人惊叹的深度社区检测\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) [![欢迎提交PR](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=flat-square)](http:\u002F\u002Fmakeapullrequest.com) ![GitHub 星标数](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FFanzhenLiu\u002Fawesome-deep-community-detection?color=yellow&label=Stars) ![GitHub 分支数](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FFanzhenLiu\u002Fawesome-deep-community-detection?color=blue&label=Forks) \n\n这是一份关于深度与非深度社区检测的论文、实现、数据集和工具的集合。\n\n- [令人惊叹的深度社区检测](#awesome-Deep-Community-Detection)\n  - [综述](#survey)\n  - [基于卷积神经网络的社区检测](#convolutional-networks-based-community-detection)\n  \t- [基于CNN的社区检测](#cnn-based-community-detection)\n  \t- [基于GCN的社区检测](#gcn-based-community-detection)\n  - [基于图注意力网络的社区检测](#graph-attention-network-based-community-detection)\n  - [基于生成对抗网络的社区检测](#graph-adversarial-network-based-community-detection)\n  - [基于自编码器的社区检测](#autoencoder-based-community-detection)\n  - [其他基于深度学习的社区检测](#other-deep-learning-based-community-detection)\n  - [非深度学习的社区检测](#non-deep-learning-based-communtiy-detection)\n  - [数据集](#datasets)\n  - [工具](#tools)  \n\n----------\n## 传统方法 _VS._ 基于深度学习的方法\n![分类体系](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFanzhenLiu_Awesome-Deep-Community-Detection_readme_bf2a11b422a3.png)\n\n----------\n## 社区检测发展时间线\n![时间线](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFanzhenLiu_Awesome-Deep-Community-Detection_readme_be85ba9ed5b9.png)\n\n----------\n## 综述\n| 论文标题 | 会议\u002F期刊 | 年份 | 资料 | \n| ---- | :----: | :----: | :----: | \n| 深度学习在社区检测中的全面综述 | IEEE TNNLS | 2022 | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9732192)] \u003Cbr> [[报告](https:\u002F\u002Fwww.aminer.cn\u002Fresearch_report\u002F60da8c5f30e4d5752f50e7af)] \u003Cbr> [[补充材料](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F359222598_Supplementary_DeepCommunityDetectionSurveypdf)]|\n| 社区检测方法综述：从统计建模到深度学习 | IEEE TKDE | 2021 | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9511798)]|\n| 深度学习在社区检测中的应用：进展、挑战与机遇 | IJCAI | 2020 | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0693.pdf)] \u003Cbr>[[报告](https:\u002F\u002Fcloud.tencent.com\u002Fdeveloper\u002Farticle\u002F1632305)]| \n| 多层网络中社区检测方法综述 | Data Min. Knowl. Discov. | 2020 | [[论文](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10618-020-00716-6)] |\n| 带属性节点的社会网络中的社区检测：综述 | Comput. Sci. Rev. | 2020 | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1574013720303865)] |\n| 网络中的社区检测：多学科综述 | J. Netw. Comput. Appl. | 2018| [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1084804518300560)] |\n| 动态网络中的社区发现：综述 | ACM Comput. Surv. | 2018 | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3172867)] |\n| 进化计算在网络社区检测中的应用：综述 | IEEE TEVC | 2018 | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8004509)] |\n| 社区分析指标：综述 | ACM Comput. Surv. | 2017 | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3091106)] |\n| 网络社区检测：回顾与可视化综述 | 预印本 | 2017 | [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.00977)] |\n| 网络中的社区检测：用户指南 | Phys. Rep. | 2016 | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0370157316302964)] |\n| 社会网络中的社区检测 | WIREs Data Min. Knowl. Discov. | 2016 | [[论文](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fwidm.1178)]|\n| 网络中重叠社区检测：现状与比较研究| ACM Comput. Surv. | 2013 | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F2501654.2501657)] |\n| 有向网络中的聚类与社区检测：综述 | Phys. Rep. | 2013 | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0370157313002822)] |\n| 图中的社区检测 | Phys. Rep. | 2010 | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0370157309002841)] |\n\n----------\n## 卷积神经网络-based社区检测\n### 基于CNN的社区检测\n| 论文标题 | 会议\u002F期刊 | 年份 | 方法 | 资料 | \n| ---- | :----: | :----: | :----: | :----: | \n| 基于CNN的归纳式表示学习，用于部分未见的属性网络 | IEEE TNSE | 2021 | IEPAN | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9314087)] |\n| 半监督在线社交网络社区检测的深度学习方法 | Knowl.-Based Syst. | 2021 | SparseConv2D | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0950705121006079)] |\n| 基于卷积神经网络的边分类，用于复杂网络中的社区检测 | Physica A | 2020 | ComNet-R | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0378437120304271)] |\n| 基于深度学习的社区检测方法 | SAC | 2019 | SparseConv | [[论文](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3297280.3297574)] |\n| 拓扑不完整网络中的深度社区检测 | Physica A | 2017 | Xin _et al._ | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0378437116308342)] |\n\n### 基于图卷积网络的社区检测\n| 论文标题 | 会议\u002F期刊 | 年份 | 方法 | 资料链接 |\n| ---- | :----: | :----: | :----: | :----: | \n|复指数图卷积网络 | 《信息科学》 | 2023 | CEGCN | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2023.119041)] [[代码](https:\u002F\u002Fgithub.com\u002FDaffominga\u002Fcegcn)] |\n|基于社区视角与图卷积网络的社区检测 | 《专家系统及其应用》 | 2023 | CPGC | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417423012502)] |\n|基于图神经网络的异质问答社区检测 | 《信息科学》 | 2023 | HCDBG | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2022.10.126)] |\n|利用图卷积网络在复杂网络上进行重叠社区检测 | 《计算机通信》 | 2023 | CDMG | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.comcom.2022.12.008)] |\n|Deep MinCut：从社区检测中学习节点嵌入 | 《模式识别》 | 2022 | DMC | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2022.109126)] |\n|二分网络中基于模块度的端到端社区协同划分 | CIKM | 2022 | BiCoN+GCN | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3511808.3557309)] |\n|CLARE：一种半监督社区检测算法 | KDD | 2022 | CLARE | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3534678.3539370)] [[代码](https:\u002F\u002Fgithub.com\u002FFDUDSDE\u002FKDD2022CLARE)] |\n|用于联合节点表示学习和聚类的高效图卷积 | WSDM | 2022 | GCC | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3488560.3498533)] [[代码](https:\u002F\u002Fgithub.com\u002Fchakib401\u002Fgraph_convolutional_clustering)] |\n|通过最大化速率降低进行几何图表示学习 | WWW | 2022 | $G^2R$ | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3485447.3512170)] [[代码](https:\u002F\u002Fgithub.com\u002Fahxt\u002FG2R)] |\n|RepBin：基于约束的图表示学习用于宏基因组分箱 | AAAI | 2022 | RepBin | [[论文](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-4979.XueH.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fxuehansheng\u002FRepBin)] |\n|SSSNET：半监督有向网络聚类 | SDM | 2022 | SSSNET | [[论文](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2110.06623.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FSherylHYX\u002FSSSNET_Signed_Clustering)] |\n|随机块模型上图卷积网络的学习保证 | ICLR | 2022 | GCN-SBM | [[论文](https:\u002F\u002Fopenreview.net\u002Fforum?id=dpXL6lz4mOQ)] |\n|当卷积网络遇上时序异质图：一种有效的社区检测方法 | IEEE TKDE | 2021 | THGCN | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9479741)] |\n|多视图对比图聚类 | NIPS | 2021 | MCGC | [[论文](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002F10c66082c124f8afe3df4886f5e516e0-Paper.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FPanern\u002FMCGC)] |\n|结合联合表示聚类的去偏置图对比学习 | IJCAI | 2021 | Zhao _et al._ | [[论文](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0473.pdf)] |\n|面向属性图聚类的谱嵌入网络 | 《神经网络》 | 2021 | SENet | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0893608021002227)] |\n|基于图卷积网络的无监督属性图社区检测 | 《神经计算》 | 2021 | SGCN | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0925231221008110)] |\n|用于属性图嵌入的自适应图编码器 | KDD | 2020 | AGE | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3394486.3403140)][[代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FAGE)] |\n|CommDGI：面向社区检测的深度图信息最大化 | CIKM | 2020 | CommDGI | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412042)] |\n|深入探索：图卷积梯形网络 | AAAI | 2020 | GCLN | [[论文](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5673\u002F5529)] |\n|促进独立性的图解耦网络 | AAAI | 2020 | IPGDN | [[论文](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5929\u002F5785)] |\n|使用线图神经网络进行监督式社区检测 | ICLR | 2019 | LGNN | [[论文](https:\u002F\u002Fopenreview.net\u002Fpdf?id=H1g0Z3A9Fm)][[代码](https:\u002F\u002Fgithub.com\u002Fzhengdao-chen\u002FGNN4CD)] |\n|图卷积网络与马尔可夫随机场的结合：属性网络中的半监督社区检测 | AAAI | 2019 | MRFasGCN | [[论文](https:\u002F\u002Fwww.aaai.org\u002Fojs\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3780\u002F3658)] |\n|利用图神经网络进行重叠社区检测 | DLG Workshop, KDD | 2019 | NOCD | [[论文](https:\u002F\u002Fdeep-learning-graphs.bitbucket.io\u002Fdlg-kdd19\u002Faccepted_papers\u002FDLG_2019_paper_3.pdf)][[代码](https:\u002F\u002Fgithub.com\u002Fshchur\u002Foverlapping-community-detection)] |\n|通过自适应图卷积进行属性图聚类 | IJCAI | 2019 | AGC | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0601.pdf)][[代码](https:\u002F\u002Fgithub.com\u002Fkarenlatong\u002FAGC-master)] |\n|CayleyNets：具有复有理谱滤波器的图卷积神经网络 | IEEE TSP | 2019 | CayleyNets | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8521593)][[代码](https:\u002F\u002Fgithub.com\u002Famoliu\u002FCayleyNet)] |\n\n----------\n## 基于图注意力网络的社区检测\n| 论文标题 | 会议\u002F期刊 | 年份 | 方法 | 资料链接 |\n| ---- | :----: | :----: | :----: | :----: | \n|CSAT：用于属性缺失网络社区检测的对比采样-聚合Transformer | IEEE TCSS | 2023 | CSAT | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10210121)] |\n|用于多层网络社区检测的图增强注意力模型 | 《专家系统及其应用》 | 2023 | GEAM | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417423010540)][[代码](https:\u002F\u002Fgithub.com\u002FHustMinsLab\u002FGEAM)] |\n|用于联合表示的层次化注意力网络——面向属性社区检测 | 《神经计算与应用》 | 2022 | HiAN | [[论文](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs00521-021-06723-y)] |\n|从异质图中检测社区：一种基于上下文路径的图神经网络模型 | CIKM | 2021 | \u003Cnobr> CP-GNN \u003Cnobr> | [[论文](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.02058.pdf)][[代码](https:\u002F\u002Fgithub.com\u002FRManLuo\u002FCP-GNN)] |\n|HDMI：高阶深度多层信息最大化 | WWW | 2021 | HDMI | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002FfullHtml\u002F10.1145\u002F3442381.3449971)][[代码](https:\u002F\u002Fgithub.com\u002Fbaoyujing\u002FHDMI)] |\n|具有共对比学习的自监督异质图神经网络 | KDD | 2021 | HeCo | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467415)][[代码](https:\u002F\u002Fgithub.com\u002Fliun-online\u002FHeCo)] |\n|无监督属性型多层网络嵌入 | AAAI | 2020 | DMGI | [[论文](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5985)][[代码](https:\u002F\u002Fgithub.com\u002Fpcy1302\u002FDMGI)] |\n|MAGNN：用于异质图嵌入的元路径聚合图神经网络 | WWW | 2020 | MAGNN | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380297)][[代码](https:\u002F\u002Fgithub.com\u002Fcynricfu\u002FMAGNN)] |\n\n----------\n\n## 基于图对抗网络的社区检测\n| 论文标题 | 会议\u002F期刊 | 年份 | 方法 | 资料 | \n| ---- | :----: | :----: | :----: | :----: |  \n|CANE：基于对抗训练的社区感知网络表示学习 |Knowl. Inf. Syst. | 2021 | CANE | [[论文](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007%2Fs10115-020-01521-9)] | \n|自训练增强：结合对抗学习的网络表示与重叠社区检测 | IEEE TNNLS | 2021 | ACNE \u003Cbr> ACNE-ST \u003Cbr> | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9451542)] |\n|用于符号网络精确社区检测的平衡三角形对抗学习 |ICDM | 2021 | ABC | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9679159)] | \n|SEAL：利用生成对抗网络学习社区检测启发式方法 | KDD | 2020 | SEAL | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3394486.3403154)][[代码](https:\u002F\u002Fgithub.com\u002Fyzhang1918\u002Fkdd2020seal)] |\n|多分类不平衡图卷积网络学习 | IJCAI | 2020 | DR-GCN | [[论文](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2020\u002F0398.pdf)] |\n|JANE：联合对抗网络表示学习 | IJCAI | 2020| JANE | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0192.pdf)] |\n|ProGAN：基于邻近关系的生成对抗网络表示学习 | KDD | 2019 | ProGAN | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3292500.3330866)] |\n|CommunityGAN：利用生成对抗网络进行社区检测 | WWW | 2019 | CommunityGAN | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3308558.3313564)][[代码](https:\u002F\u002Fgithub.com\u002FSamJia\u002FCommunityGAN)] |\n\n----------\n\n## 基于自编码器的社区检测\n| 论文标题 | 会议\u002F期刊 | 年份 | 方法 | 材料 |\n| ---- | :----: | :----: | :----: | :----: |\n|用于多层网络社区检测的图卷积融合模型 | Data Min. Knowl. Discov. | 2023 | GCFM | [[论文](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10618-023-00932-w)] |\n|利用变分自编码器进行社区检测的新型网络核心结构提取算法 | Expert Syst. Appl. | 2023 | CSEA | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eswa.2023.119775)][[代码](https:\u002F\u002Fgithub.com\u002FPeterWana\u002FCSEA)] |\n|基于无监督属性网络嵌入的社区检测 | Expert Syst. Appl. | 2023 | CDBNE | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eswa.2022.118937)][[代码](https:\u002F\u002Fgithub.com\u002Fxidizxc\u002FCDBNE)] |\n|通过网络嵌入探索时间社区结构 | IEEE TCYB | 2022 | VGRGMM | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9768181)]|\n|图社区信息最大化 | ACM TKDD | 2022 | GCI | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3480244)] |\n|结合社区检测和卷积自编码器的多模态非欧几里得脑网络分析 | IEEE TETCI | 2022 | M2CDCA | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9773106)] |\n|面向属性图节点聚类的深度邻域感知嵌入 | Pattern Recognit. | 2022 | DNENC | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.patcog.2021.108230)] |\n|利用图卷积自编码器进行属性图中的半监督重叠社区检测 | Inf. Sci. | 2022 | SSGCAE | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2022.07.036)] |\n|基于深度学习的加权网络社区检测算法 | Appl. Math. Comput. | 2021 | WCD | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0096300321000606)] |\n|DNC：一种基于深度神经网络、面向聚类的网络嵌入算法 | J. Netw. Comput. Appl. | 2021 | DNC | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1084804520303209)] |\n|利用图注意力自编码器增强基于非负矩阵分解的社区检测 | IEEE TBD | 2021 | NMFGAAE | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9512416)]|\n|用于多视图聚类的自监督图卷积网络 | IEEE TMM | 2021 | SGCMC | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9472979)] |\n|图嵌入聚类：具有聚类特异性分布的图注意力自编码器 | Neural Netw. | 2021 | GEC-CSD | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0893608021002008)][[代码](https:\u002F\u002Fgithub.com\u002Fxdweixia\u002FSGCMC)] |\n|用于动态社区检测的进化自编码器 | Sci. China Inf. Sci. | 2020 | \u003Cnobr> sE-Autoencoder \u003Cnobr> | [[论文](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11432-020-2827-9)] |\n|基于堆叠自编码器并通过集成聚类框架实现的社区检测方法 | Inf. Sci. | 2020 | CDMEC | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS002002552030270X)] |\n|面向社区中心的图卷积网络用于无监督社区检测 | IJCAI | 2020 | GUCD | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0486.pdf)] |\n|结构化深度聚类网络 | WWW | 2020 | SDCN | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3366423.3380214)][[代码](https:\u002F\u002Fgithub.com\u002Fbdy9527\u002FSDCN)] |\n|用于多视图图聚类的One2Multi图自编码器 | WWW | 2020 | One2Multi | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3366423.3380079)][[代码](https:\u002F\u002Fgithub.com\u002Fgooglebaba\u002FWWW2020-O2MAC)] |\n|用于聚类的多视图属性图卷积网络 | IJCAI | 2020 | MAGCN | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2020\u002F0411.pdf)] |\n|通过注意力交叉图关联实现的深度多图聚类 | WSDM | 2020 | DMGC | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3336191.3371806)][[代码](https:\u002F\u002Fgithub.com\u002Fflyingdoog\u002FDMGC)] |\n|利用三元闭包提高图自编码器的有效解码能力 | AAAI | 2020 | TGA \u003Cbr> TVGA \u003Cbr> | [[论文](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F5437\u002F5293)] |\n|通过梯形伽马变分自编码器进行图表示学习 | AAAI | 2020 | LGVG | [[论文](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F6013\u002F5869)] |\n|使用深度传递自编码器在社交网络中实现高性能社区检测 | Inf. Sci. | 2019 | \u003Cnobr> Transfer-CDDTA \u003Cnobr> | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0020025519303251)] |\n|属性图聚类：一种深度注意力嵌入方法 | IJCAI | 2019 | DAEGC | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0509.pdf)] |\n|随机块模型与图神经网络的结合 | ICML | 2019 | DGLFRM | [[论文](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fmehta19a\u002Fmehta19a.pdf)][[代码](https:\u002F\u002Fgithub.com\u002Fnikhil-dce\u002FSBM-meet-GNN)] |\n|利用拉普拉斯特征映射进行变分图嵌入和聚类 | IJCAI | 2019 | VGECLE | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2019\u002F0297.pdf)] |\n|优化变分图自编码器以用于社区检测 | BigData | 2019 | VGAECD-OPT | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9006123)] |\n|通过深度联合重建进行整合性网络嵌入 | IJCAI | 2018 | UWMNE | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F0473.pdf)] |\n|深度属性网络嵌入 | IJCAI | 2018 | DANE | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F0467.pdf)][[代码](https:\u002F\u002Fgithub.com\u002Fgaoghc\u002FDANE)] |\n|用于有向网络图表示学习的深度网络嵌入 | IEEE TCYB | 2018 | DNE-SBP | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8486671)][[代码](https:\u002F\u002Fgithub.com\u002Fshenxiaocam\u002FDeep-network-embedding-for-graph-representation-learning-in-signed-networks)] |\n|DFuzzy：一种基于深度学习的大规模图模糊聚类模型 | Knowl. Inf.  Syst. | 2018 | DFuzzy | [[论文](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10115-018-1156-3)] |\n|利用变分自编码器学习社区结构 | ICDM | 2018 | VGAECD | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8594831)] |\n|用于图嵌入的对抗正则化图自编码器 | IJCAI | 2018 | ARGA \u003Cbr> ARVGA \u003Cbr> | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2018\u002F0362.pdf)][[代码](https:\u002F\u002Fgithub.com\u002FRuiqi-Hu\u002FARGA)]|\n|BL-MNE：通过对齐自编码器的广义学习实现新兴异构社交网络嵌入 | ICDM | 2017 | DIME | [[论文](https:\u002F\u002Fdoi.org\u002F10.1109\u002FICDM.2017.70)][[代码](http:\u002F\u002Fwww.ifmlab.org\u002Ffiles\u002Fcode\u002FAligned-Autoencoder.zip)] |\n|MGAE：用于图聚类的边缘化图自编码器 | CIKM | 2017 | MGAE | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3132847.3132967)][[代码](https:\u002F\u002Fgithub.com\u002FFakeTibbers\u002FMGAE)] |\n|带有动态嵌入的图聚类 | 预印本 | 2017 | GRACE | [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.08249)] |\n|基于模块度的深度学习社区检测 | IJCAI | 2016 | 半DRN | [[论文](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F16\u002FPapers\u002F321.pdf)][[代码](http:\u002F\u002Fyangliang.github.io\u002Fcode\u002FDC.zip)] |\n|用于学习图表示的深度神经网络 | AAAI | 2016 | DNGR | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3015812.3015982)] |\n|用于图聚类的深度表示学习 | AAAI | 2014 | GraphEncoder | [[论文](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI14\u002Fpaper\u002Fview\u002F8527\u002F8571)][[代码](https:\u002F\u002Fgithub.com\u002Fquinngroup\u002Fdeep-representations-clustering)] |\n\n----------\n\n\n## 其他基于深度学习的社区发现\n| 论文标题 | 会议\u002F期刊 | 年份 | 方法 | 资料 | \n| ---- | :----: | :----: | :----: | :----: | \n| 用于社区发现的对比式深度非负矩阵分解 | ICASSP | 2024 | CDNMF | [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.02357)][[代码](https:\u002F\u002Fgithub.com\u002F6lyc\u002FCDNMF)] |\n| 基于双曲空间的图社区学习方法 | Data Min. Knowl. Discov. | 2023 | RComE | [[论文](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10618-022-00902-8)][[代码](https:\u002F\u002Fwww.github.com\u002Ftgeral68\u002FHyperbolicGraphAndGMM)] |\n| 深度交替非负矩阵分解 | Knowl.-Based Syst. | 2022 | DA-NMF | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.109210)] |\n| CGC：用于社区发现与追踪的对比图聚类 | WWW | 2022 | CGC | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3485447.3512160)] |\n| 基于双重相关性降低的深度图聚类 | AAAI | 2022 | DCRN | [[论文](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-5928.LiuY.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fyueliu1999\u002FDCRN)] |\n| 聚类感知的异构信息网络嵌入 | WSDM | 2022 | VaCA-HINE | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498385)] |\n| 基于图滤波器的多视图属性图聚类 | IJCAI | 2021 | MvAGC | [[论文](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0375.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FMvAGC)] |\n| 用于自演化层次社区发现的深度学习框架 | CIKM | 2021 | ReinCom | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3459637.3482223)] |\n| 用于节点表示和社区发现的联合无监督嵌入学习 | ECML-PKDD | 2021 | J-ENC | [[论文](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-86520-7_2)] |\n| 基于模块化深度非负矩阵分解的社区发现 | Int. J. Pattern Recognit. Artif. Intell. | 2020 | MDNMF | [[论文](https:\u002F\u002Fwww.worldscientific.com\u002Fdoi\u002Fabs\u002F10.1142\u002FS0218001421590060)] |\n| 用于社区发现的深度自编码器式非负矩阵分解 | CIKM | 2018 | DANMF | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3269206.3271697)][[代码](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002FDANMF)] |\n| 基于深度稀疏滤波的网络社区发现 | Pattern Recognit. | 2018 | DSFCD | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS003132031830116X)] |\n| 用于社区发现的非负对称编解码器方法 | CIKM | 2017 | Sun _et al._ | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3132847.3132902)] |\n\n----------\n\n## 非深度学习的社区发现\n| 论文标题 | 会议\u002F期刊 | 年份 | 方法 | 资料 |\n| ---- | :----: | :----: | :----: | :----: |\n| CataBEEM：在节点级社区发现模型中整合潜在交互类别以处理网络数据 | ICML | 2023 | CataBEEM | [[论文](https:\u002F\u002Fproceedings.mlr.press\u002Fv202\u002Fzhang23h.html)][[代码](https:\u002F\u002Fgithub.com\u002FYuhuaZhang1995\u002FCataBEEM)] |\n| 基于节点中心性的非负矩阵分解用于社区发现 | ACM TKDD | 2023 | NCNMF | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Ffull\u002F10.1145\u002F3578520)][[代码](https:\u002F\u002Fgithub.com\u002FwowoHead\u002FNCNMF)] |\n| 社交网络上的双重结构一致性保持社区发现 | IEEE TKDE | 2023 | DSCPCD | [[论文](https:\u002F\u002Fdoi.org\u002F10.1109\u002FTKDE.2022.3230502)][[代码](https:\u002F\u002Fgithub.com\u002Fwyy-cs\u002FDSCPCD)] |\n| 对称性和图双正则化的非负矩阵分解用于精确社区发现 | IEEE TASAE | 2023 | B-NMF | [[论文](https:\u002F\u002Fdoi.org\u002F10.1109\u002FTASE.2023.3240335)] |\n| 基于客流的多视角地铁站聚类：一种基于函数型数据边的网络社区发现方法 | Data Min. Knowl. Discov. | 2023 | F\u003Csup>2\u003C\u002Fsup>MVNCD | [[论文](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10618-023-00916-w)] |\n| 基于模体感知的多层网络社区发现算法 | Knowl.-Based Syst. | 2023 | CDMA | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.110136)] |\n| 通过类似自编码器的非负张量分解进行社区发现 | IEEE TNNLS | 2022 | ANTD | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9904739)] |\n| 图正则化的非负矩阵分解用于属性网络中的社区发现 | IEEE TNSE | 2022 | AGNMF-AN | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9904900)] |\n| 节点属性网络中的社区建模与检测 | IEEE TKDE | 2022 | CRSBM | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9852668)] |\n| 社区发现中拓扑与内容之间的权衡：基于自适应编码器-解码器的 NMF 方法 | Expert Syst. Appl. | 2022 | ANMF | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eswa.2022.118230)] |\n| 属性子空间中的社区发现 | Inf. Sci. | 2022 | SOA | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2022.04.047)] |\n| 图数据科学中的可解释性：社区发现的可解释性、可重复性和可再现性 | IEEE Signal Process. Mag. | 2022 | -- | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9810084)] |\n| 随机块模型的差分隐私社区发现 | ICML | 2022 | Seif _et al._ | [[论文](http:\u002F\u002F128.84.4.18\u002Fabs\u002F2202.00636)] |\n| 基于进化多任务优化和进化聚类集成的多层网络社区发现 | IEEE TEVC | 2022 | BSMCD | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9802693)] |\n| 细粒度属性图聚类 | SDM | 2022 | FGC | [[论文](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977172.42)] [[代码](https:\u002F\u002Fgithub.com\u002Fsckangz\u002FFGC)] |\n| HB-DSBM：从社区层面到节点层面的动态复杂网络建模 | IEEE TNNLS | 2022 | HB-DSBM | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9721420)] |\n| PMCDM：多层网络中的隐私保护多分辨率社区发现 | Knowl.-Based Syst. | 2022 | PMCDM | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.knosys.2022.108542)] |\n| 为社区发现重新排列“不可分割”的块 | IEEE TKDE | 2022 | RaidB | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9771068)] |\n| 考虑信息扩散的似然最大化优化用于社区发现 | Inf. Sci. | 2022 | EM-CD \u003Cbr> L-Louvain \u003Cbr> | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0020025522003334)] |\n| 部分可观测社交网络中的社区发现 | ACM TKDD | 2022 | KroMFac | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3461339)] |\n| 通过超图聚类发现多元且经验丰富的群体 | SDM | 2022 | Amburg _et al._ | [[论文](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fepdf\u002F10.1137\u002F1.9781611977172.17)] [[代码](https:\u002F\u002Fgithub.com\u002Filyaamburg\u002Ffair-clustering-for-diverse-and-experienced-groups)] |\n| 图中的社区发现：一种嵌入方法 | IEEE TNSE | 2022 | SENMF | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9626627)] |\n| 使用局部群体同化进行社区发现 | Expert Syst. Appl. | 2022 | LGA | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417422010600)] |\n| 利用网络社区发现识别新闻中的早期预警信号 | AAAI | 2022 | Le Vine _et al._ | [[论文](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F21503\u002F21252)] |\n| Residual2Vec：利用随机图去偏图嵌入 | NIPS | 2021 | residual2vec | [[论文](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002Fca9541826e97c4530b07dda2eba0e013-Paper.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fskojaku\u002Fresidual2vec)] |\n| 流式信念传播用于社区发现 | NIPS | 2021 | StSBM | [[论文](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2021\u002Ffile\u002Fe2a2dcc36a08a345332c751b2f2e476c-Paper.pdf)] |\n| 三角形感知谱稀疏化器与社区发现 | KDD | 2021 | Sotiropoulos _et al._ | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3447548.3467260)] [[代码](https:\u002F\u002Fwww.dropbox.com\u002Fs\u002F0p0ybkpx19jt3ii\u002FcodeKDDTriangleAware.zip?dl=0)] |\n| 在存在缺失边的网络上进行自引导社区发现 | IJCAI | 2021 | SGCD | [[论文](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0483.pdf)] |\n| 大规模属性图上的高效可扩展聚类 | WWW | 2021 | ACMin | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3442381.3449875)] [[代码](https:\u002F\u002Fgithub.com\u002FAnryYang\u002FACMin)] |\n| 通过并行相关聚类实现可扩展的社区发现 | VLDB | 2021 | Shi _et al._ | [[论文](http:\u002F\u002Fvldb.org\u002Fpvldb\u002Fvol14\u002Fp2305-shi.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fjeshi96\u002Fparallel-correlation-clustering)] |\n| 基于邻近性的群体形成博弈模型用于社交网络中的社区发现 | Knowl.-Based Syst. | 2021 | PBCD | [[论文](https:\u002F\u002Flinkinghub.elsevier.com\u002Fretrieve\u002Fpii\u002FS0950705120307991)] |\n| 随机初始化何时有帮助：关于社区发现的变分推断研究 | J. Mach. Learn. Res. | 2021 | BCAVI | [[论文](https:\u002F\u002Fwww.jmlr.org\u002Fpapers\u002Fvolume22\u002F19-630\u002F19-630.pdf)] |\n| 通过网络生成过程进行紧凑性保持的社区计算 | IEEE TETCI | 2021 | FCOCD | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9548676)] |\n| 基于贝叶斯生成模型识别多语义社区 | IEEE TBD | 2021 | ICMS | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9632396)] |\n| 网络嵌入增强的贝叶斯模型用于复杂网络中的广义社区发现 | Inf. Sci. | 2021 | NEGCD | [[论文](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.ins.2021.06.020)] |\n| 多目标进化聚类用于大规模动态社区发现 | Inf. Sci. | 2021 | \u003Cnobr> DYN-MODPSO \u003Cnobr> | [[论文](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0020025520311117)] |\n| 一种联合社区发现模型：通过带有注意力机制的因子图整合有向和无向概率图模型 | IEEE TBD | 2021 | AdaMRF | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9511816)] |\n| SimClusters：Twitter 上基于社区的异构推荐表示 | KDD | 2020 | SimClusters | [[论文](https:\u002F\u002Fdoi.org\u002F10.1145\u002F3394486.3403370)] [[代码](https:\u002F\u002Fgithub.com\u002Ftwitter\u002Fsbf)] |\n| 用于网络社区发现的进化马尔可夫动力学 | IEEE TKDE | 2020 | ePMCL | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9099469)] |\n| 基于网络约简的多目标进化算法用于大规模复杂网络中的社区发现 | IEEE TCYB | 2020 | RMOEA | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8486719)] |\n| 将群体同质性和个体主题个性相结合可以更好地建模网络社区 | ICDM | 2020 | GHIPT | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9338379)] |\n| 基于记忆算法的社区保全网络嵌入 | IEEE TETCI | 2020 | MemeRep | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8449095)] |\n| 检测动态社交网络中的演化社区结构 | World Wide Web J. | 2020 | DECS | [[论文](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11280-019-00710-z)] [[代码](https:\u002F\u002Fgithub.com\u002FFanzhenLiu\u002FDECS)] |\n| EdMot：面向模体感知的社区发现的边增强方法 | KDD | 2019 | EdMot | [[论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330882)] |\n| LPANNI：在大规模复杂网络中使用标签传播进行重叠社区发现 | IEEE TKDE | 2019 | LPANNI | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8443129)] |\n| 从多智能体视角检测智能电网中的产消者社区 | IEEE TSMC | 2019 | PVMAS | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8660684)] |\n| 从多智能体视角对分布式和动态网络进行本地社区挖掘 | IEEE TCYB | 2016 | AOCCM | [[论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7124425)] |\n| 用于复杂网络中高质量社区发现的一般优化技术 | Phys. Rev. E | 2014 | Combo | [[论文](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.90.012811)] |\n| 用于社区发现和图划分的谱方法 | Phys. Rev. E | 2013 | -- | [[论文](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.88.042822)] |\n| 随机块模型与网络中的社区结构 | Phys. Rev. E | 2011 | DCSBM | [[论文](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.83.016107)] |\n\n----------\n\n\n## 数据集\n### 引文\u002F合著网络\n- Citeseer、Cora、Pubmed https:\u002F\u002Flinqs.soe.ucsc.edu\u002Fdata\n- DBLP http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fcom-DBLP.html\n- 化学、计算机科学、医学、工程 http:\u002F\u002Fkddcup2016.azurewebsites.net\u002F\n### 在线社交网络\n- Facebook http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fego-Facebook.html\n- Epinions http:\u002F\u002Fwww.epinions.com\u002F\n- Youtube http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fcom-Youtube.html\n- Last.fm https:\u002F\u002Fwww.last.fm\u002F\n- LiveJournal http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fsoc-LiveJournal1.html\n- Gplus http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Fego-Gplus.html\n### 传统社交网络\n- 手机通话 http:\u002F\u002Fwww.cs.umd.edu\u002Fhcil\u002FVASTchallenge08\u002F\n- Enron 邮件 http:\u002F\u002Fwww.cs.cmu.edu\u002F~enron\u002F\n- 友谊关系 https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F2501654.2501657\n- Rados http:\u002F\u002Fnetworkrepository.com\u002Fia-radoslaw-email.php \n- 空手道俱乐部、美式足球、海豚 http:\u002F\u002Fwww-personal.umich.edu\u002F~mejn\u002Fnetdata\u002F\n### 网页网络\n- IMDb https:\u002F\u002Fwww.imdb.com\u002F\n- Wiki https:\u002F\u002Flinqs.soe.ucsc.edu\u002Fdata\n### 商品共同购买网络\n- Amazon http:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002F#amazon\n### 其他网络\n- Internet http:\u002F\u002Fwww-personal.umich.edu\u002F~mejn\u002Fnetdata\u002F\n- Java https:\u002F\u002Fgithub.com\u002Fgephi\u002Fgephi\u002Fwiki\u002FDatasets\n- 超文本 http:\u002F\u002Fwww.sociopatterns.org\u002Fdatasets\n \n ----------\n## 工具\n- Gephi https:\u002F\u002Fgephi.org\u002F\n- Pajek http:\u002F\u002Fmrvar.fdv.uni-lj.si\u002Fpajek\u002F\n- LFR https:\u002F\u002Fwww.santofortunato.net\u002Fresources\n\n----------\n**免责声明**\n\n如有任何问题，请随时与我们联系。\n邮箱：\u003Cu>fanzhen.liu@hdr.mq.edu.au\u003C\u002Fu>, \u003Cu>xing.su2@hdr.mq.edu.au\u003C\u002Fu>","# Awesome-Deep-Community-Detection 快速上手指南\n\n`Awesome-Deep-Community-Detection` 并非一个单一的独立软件包，而是一个汇集了社区检测（Community Detection）领域前沿论文、代码实现、数据集和工具的精选列表。本指南将指导开发者如何利用该资源库快速找到并运行基于深度学习的社区检测算法。\n\n## 环境准备\n\n由于列表中包含多种不同架构的模型（如 CNN, GCN, GAT, GAN 等），具体的依赖项因所选算法而异。但大多数现代深度学习实现都遵循以下通用环境要求：\n\n*   **操作系统**: Linux (推荐 Ubuntu 20.04+), macOS, 或 Windows (WSL2 推荐)\n*   **Python 版本**: 3.7 - 3.10 (具体视模型而定，建议创建虚拟环境)\n*   **核心框架**: PyTorch (最常用) 或 TensorFlow\u002FKeras\n*   **图神经网络库**: `torch-geometric` (PyG), `DGL`, 或 `Spektral`\n*   **基础依赖**: `numpy`, `scipy`, `scikit-learn`, `networkx`, `pandas`\n\n**前置依赖安装示例 (以 PyTorch 生态为例):**\n\n```bash\n# 创建虚拟环境\npython -m venv cd_env\nsource cd_env\u002Fbin\u002Factivate  # Windows: cd_env\\Scripts\\activate\n\n# 安装 PyTorch (推荐使用国内镜像源加速)\npip install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\n\n# 安装图神经网络核心库\npip install torch-geometric\n\n# 安装通用数据处理库\npip install numpy scipy scikit-learn networkx pandas matplotlib\n```\n\n## 安装步骤\n\n由于这是一个资源列表，\"安装\"实际上是指克隆仓库并获取你感兴趣的具体算法代码。\n\n1.  **克隆仓库**:\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002FFanzhenLiu\u002Fawesome-deep-community-detection.git\n    cd awesome-deep-community-detection\n    ```\n\n2.  **选择算法**:\n    浏览 `README.md` 中的分类（如 `GCN-based Community Detection`），找到带有 `[[Code]]` 标记的项目。例如，选择 **CLARE** (KDD 2022) 或 **AGE** (KDD 2020)。\n\n3.  **获取具体实现**:\n    点击对应论文的 `[[Code]]` 链接进入其独立仓库，或直接使用 `git clone` 下载。以 **AGE** 为例：\n    ```bash\n    # 进入上级目录后克隆具体算法仓库\n    cd ..\n    git clone https:\u002F\u002Fgithub.com\u002Fthunlp\u002FAGE.git\n    cd AGE\n    ```\n\n4.  **安装该算法的特定依赖**:\n    大多数独立仓库都会提供 `requirements.txt`。\n    ```bash\n    pip install -r requirements.txt\n    ```\n    *注：如果项目中没有 `requirements.txt`，请参考上述“环境准备”中的通用依赖进行安装。*\n\n## 基本使用\n\n以下以 **AGE (Adaptive Graph Encoder)** 为例，展示如何运行一个典型的深度社区检测模型。其他模型的运行逻辑类似（通常为：准备数据 -> 配置参数 -> 运行训练\u002F测试脚本）。\n\n### 1. 准备数据\n大多数算法使用标准的图数据集（如 Cora, Citeseer, Pubmed）。数据通常位于 `data\u002F` 目录下。如果没有，需手动下载并放置。\n\n```bash\n# 假设当前在 AGE 项目根目录\nls data\u002F\n# 应看到 cora\u002F, citeseer\u002F 等文件夹\n```\n\n### 2. 运行模型\n执行主训练脚本。通常可以通过命令行参数指定数据集、聚类数量（communities）和随机种子。\n\n```bash\n# 基本运行命令示例\npython main.py --dataset cora --n_clusters 7 --seed 42\n```\n\n*   `--dataset`: 指定数据集名称。\n*   `--n_clusters`: 指定预期的社区数量（对于有监督或半监督任务，这通常是已知的类别数）。\n*   `--seed`: 设置随机种子以保证结果可复现。\n\n### 3. 查看结果\n运行结束后，终端通常会输出评估指标（如 NMI, ARI, ACC），并在项目目录下生成保存的模型文件或聚类结果文件。\n\n```text\nTraining finished.\nNMI: 0.5623, ARI: 0.4891, ACC: 0.6105\nResults saved to .\u002Fresults\u002Fcora_age.txt\n```\n\n### 通用开发建议\n*   **查阅原文**: 在运行具体代码前，务必点击列表中的 `[[Paper]]` 阅读论文，了解模型的输入格式要求和超参数含义。\n*   **数据格式**: 不同模型对输入图数据的格式要求不同（如 Adjacency Matrix vs. Edge List），请仔细阅读具体仓库的 `README`。\n*   **GPU 加速**: 如果数据集较大，建议在代码中启用 CUDA 加速（通常默认开启，可通过 `--device cuda` 参数控制）。","某大型电商平台的数据科学团队正试图从亿级用户社交互动图中挖掘潜在的“刷单团伙”和“营销水军”群落，以优化风控策略。\n\n### 没有 Awesome-Deep-Community-Detection 时\n- **选型迷茫**：面对层出不穷的深度学习算法（如 GCN、GAT、GAN），团队需耗费数周在 arXiv 和 GitHub 上盲目搜索，难以区分哪些模型适合处理带属性的大规模动态网络。\n- **复现困难**：找到的论文往往缺乏官方代码或数据集格式不统一，工程师需花费大量时间清洗数据并重写底层图卷积逻辑，导致项目启动严重滞后。\n- **基线缺失**：缺乏系统的传统方法与深度学习方法对比基准，难以评估新模型是否真的比 Louvain 等经典算法更有效，容易陷入“为了用深度学习而用”的误区。\n- **前沿脱节**：无法及时获取关于多层网络或重叠社区检测的最新综述，导致技术方案停留在两年前的水平，漏掉了处理复杂嵌套关系的关键机会。\n\n### 使用 Awesome-Deep-Community-Detection 后\n- **精准导航**：团队直接利用其分类目录，快速锁定了适用于“节点属性社交网络”的 GCN 和 GAT 类最新实现，将技术调研周期从数周缩短至两天。\n- **开箱即用**：通过仓库提供的标准化数据集链接和已验证的代码实现，研究人员无需重复造轮子，直接在其基础上进行微调以适应电商场景。\n- **科学决策**：参考其中详尽的综述论文和对比图表，团队迅速建立了包含传统与深度方法的完整基线体系，量化证明了深度模型在识别隐蔽团伙上的优势。\n- **视野开阔**：借助时间轴和最新综述，团队引入了针对动态演化的社区检测方案，成功捕捉到了随时间变化的作弊模式，提升了风控系统的时效性。\n\nAwesome-Deep-Community-Detection 将原本分散杂乱的学术资源转化为结构化的工程资产，让算法团队能从繁琐的文献挖掘中解脱，专注于核心业务价值的落地。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFanzhenLiu_Awesome-Deep-Community-Detection_be85ba9e.png","FanzhenLiu","Fanzhen Liu","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FFanzhenLiu_36a268b6.jpg","Postdoc @ School of Computing, Macquarie University, Sydney, Australia, primarily working on graph mining topics","Macquaire University","Sydney, Australia",null,"https:\u002F\u002Ffanzhenliu.github.io\u002F","https:\u002F\u002Fgithub.com\u002FFanzhenLiu",560,94,"2026-03-30T04:34:37","MIT",5,"","未说明",{"notes":89,"python":87,"dependencies":90},"该仓库是一个社区检测（Community Detection）领域的论文、实现、数据集和工具的资源列表（Awesome List），本身不是一个可直接运行的单一软件工具。因此，README 中未提供具体的操作系统、硬件配置或依赖库版本要求。具体的运行环境需求需参考列表中各个独立项目（如 CEGCN, CLARE, AGE 等）各自的代码仓库和文档。",[],[14,16],[93,94,95,96,97,98,99,100,101,102,103,104],"community-detection","graph-neural-network","deep-learning","deep-neural-network","network-representation-learning","graph-clustering","survey","network-embedding","graph-embedding","awesome","data-mining","graph-neural-networks","2026-03-27T02:49:30.150509","2026-04-08T07:44:43.206499",[],[]]