[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-benedekrozemberczki--karateclub":3,"tool-benedekrozemberczki--karateclub":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},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。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},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",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},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。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":82,"owner_website":83,"owner_url":84,"languages":85,"stars":90,"forks":91,"last_commit_at":92,"license":93,"difficulty_score":94,"env_os":95,"env_gpu":96,"env_ram":96,"env_deps":97,"category_tags":109,"github_topics":110,"view_count":23,"oss_zip_url":83,"oss_zip_packed_at":83,"status":16,"created_at":130,"updated_at":131,"faqs":132,"releases":163},1364,"benedekrozemberczki\u002Fkarateclub","karateclub","Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)","Karate Club 是一个专为 NetworkX 打造的 Python 无监督图学习扩展库，把节点嵌入、图嵌入、重叠\u002F非重叠社区发现等 50 余种前沿算法打包成“瑞士军刀”式的统一 API。只需几行代码，就能把社交网络、生物分子、推荐系统等图数据自动转成向量或划分社区，省去繁琐实现与调参。它尤其适合图神经网络研究者、数据科学家和需要快速原型验证的开发者；内置算法均来自 NeurIPS、KDD、AAAI 等顶会顶刊，并可直接对接 SNAP、TUD 等公开图数据集。轻量、零依赖、文档齐全，让图挖掘像调包一样简单。","\n ![Version](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fkarateclub.svg?style=plastic)\n ![License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fbenedekrozemberczki\u002Fkarateclub.svg)\n[![repo size](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frepo-size\u002Fbenedekrozemberczki\u002Fkarateclub.svg)](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Farchive\u002Fmaster.zip)\n [![Arxiv](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FArXiv-2003.04819-orange.svg)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.04819)\n[![build badge](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fworkflows\u002FCI\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Factions?query=workflow%3ACI)\n [![coverage badge](https:\u002F\u002Fcodecov.io\u002Fgh\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fbranch\u002Fmaster\u002Fgraph\u002Fbadge.svg)](https:\u002F\u002Fcodecov.io\u002Fgithub\u002Fbenedekrozemberczki\u002Fkarateclub?branch=master)\n\u003Cp align=\"center\">\n  \u003Cimg width=\"90%\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fbenedekrozemberczki_karateclub_readme_ca8cd60f8845.jpg\" \u002F>\n\u003C\u002Fp>\n\n------------------------------------------------------\n\n\n**Karate Club** is an unsupervised machine learning extension library for [NetworkX](https:\u002F\u002Fnetworkx.github.io\u002F).\n\n\nPlease look at the **[Documentation](https:\u002F\u002Fkarateclub.readthedocs.io\u002F)**, relevant **[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.04819)**, **[Promo Video](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=t212-ntxu2U)**, and **[External Resources](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fnotes\u002Fresources.html)**.\n\n*Karate Club* consists of state-of-the-art methods to do unsupervised learning on graph structured data. To put it simply it is a Swiss Army knife for small-scale graph mining research. First, it provides network embedding techniques at the node and graph level. Second, it includes a variety of overlapping and non-overlapping community detection methods. Implemented methods cover a wide range of network science ([NetSci](https:\u002F\u002Fnetscisociety.net\u002Fhome), [Complenet](https:\u002F\u002Fcomplenet.weebly.com\u002F)), data mining ([ICDM](http:\u002F\u002Ficdm2019.bigke.org\u002F), [CIKM](http:\u002F\u002Fwww.cikm2019.net\u002F), [KDD](https:\u002F\u002Fwww.kdd.org\u002Fkdd2020\u002F)), artificial intelligence ([AAAI](http:\u002F\u002Fwww.aaai.org\u002FConferences\u002Fconferences.php), [IJCAI](https:\u002F\u002Fwww.ijcai.org\u002F)) and machine learning ([NeurIPS](https:\u002F\u002Fnips.cc\u002F), [ICML](https:\u002F\u002Ficml.cc\u002F), [ICLR](https:\u002F\u002Ficlr.cc\u002F)) conferences, workshops, and pieces from prominent journals.\n\nThe newly introduced graph classification datasets are available at [SNAP](https:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002F#disjointgraphs), [TUD Graph Kernel Datasets](https:\u002F\u002Fls11-www.cs.tu-dortmund.de\u002Fstaff\u002Fmorris\u002Fgraphkerneldatasets), and [GraphLearning.io](https:\u002F\u002Fchrsmrrs.github.io\u002Fdatasets\u002F).\n\n--------------------------------------------------------------\n\n**Citing**\n\nIf you find *Karate Club* and the new datasets useful in your research, please consider citing the following paper:\n\n```bibtex\n@inproceedings{karateclub,\n       title = {{Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs}},\n       author = {Benedek Rozemberczki and Oliver Kiss and Rik Sarkar},\n       year = {2020},\n       pages = {3125–3132},\n       booktitle = {Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM '20)},\n       organization = {ACM},\n}\n```\n----------------------------------------------------------------\n\n**A simple example**\n\n*Karate Club* makes the use of modern community detection techniques quite easy (see [here](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fnotes\u002Fintroduction.html) for the accompanying tutorial). For example, this is all it takes to use on a Watts-Strogatz graph [Ego-splitting](https:\u002F\u002Fwww.eecs.yorku.ca\u002Fcourse_archive\u002F2017-18\u002FF\u002F6412\u002Freading\u002Fkdd17p145.pdf):\n\n```python\nimport networkx as nx\nfrom karateclub import EgoNetSplitter\n\ng = nx.newman_watts_strogatz_graph(1000, 20, 0.05)\n\nsplitter = EgoNetSplitter(1.0)\n\nsplitter.fit(g)\n\nprint(splitter.get_memberships())\n```\n\n----------------------------------------------------------------\n\n**Models included**\n\nIn detail, the following community detection and embedding methods were implemented.\n\n**Overlapping Community Detection**\n\n* **[DANMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.danmf.DANMF)** from Ye *et al.*: [Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002FDANMF\u002Fblob\u002Fmaster\u002F18DANMF.pdf) (CIKM 2018)\n\n* **[M-NMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.mnmf.M_NMF)** from Wang *et al.*: [Community Preserving Network Embedding](https:\u002F\u002Faaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI17\u002Fpaper\u002Fview\u002F14589) (AAAI 2017)\n\n* **[Ego-Splitting](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.ego_splitter.EgoNetSplitter)** from Epasto *et al.*: [Ego-splitting Framework: from Non-Overlapping to Overlapping Clusters](https:\u002F\u002Fwww.eecs.yorku.ca\u002Fcourse_archive\u002F2017-18\u002FF\u002F6412\u002Freading\u002Fkdd17p145.pdf) (KDD 2017)\n\n* **[NNSED](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.nnsed.NNSED)** from Sun *et al.*: [A Non-negative Symmetric Encoder-Decoder Approach for Community Detection](http:\u002F\u002Fwww.bigdatalab.ac.cn\u002F~shenhuawei\u002Fpublications\u002F2017\u002Fcikm-sun.pdf) (CIKM 2017)\n\n* **[BigClam](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.bigclam.BigClam)** from Yang and Leskovec: [Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach](http:\u002F\u002Finfolab.stanford.edu\u002F~crucis\u002Fpubs\u002Fpaper-nmfagm.pdf) (WSDM 2013)\n\n* **[SymmNMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.symmnmf.SymmNMF)** from Kuang *et al.*: [Symmetric Nonnegative Matrix Factorization for Graph Clustering](https:\u002F\u002Fwww.cc.gatech.edu\u002F~hpark\u002Fpapers\u002FDaDingParkSDM12.pdf) (SDM 2012)\n\n**Non-Overlapping Community Detection**\n\n* **[GEMSEC](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.gemsec.GEMSEC)** from Rozemberczki *et al.*: [GEMSEC: Graph Embedding with Self Clustering](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.03997) (ASONAM 2019)\n\n* **[EdMot](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.edmot.EdMot)** from Li *et al.*: [EdMot: An Edge Enhancement Approach for Motif-aware Community Detection](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04560) (KDD 2019)\n\n* **[SCD](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.scd.SCD)** from Prat-Perez *et al.*: [High Quality, Scalable and Parallel Community Detectionfor Large Real Graphs](http:\u002F\u002Fwwwconference.org\u002Fproceedings\u002Fwww2014\u002Fproceedings\u002Fp225.pdf) (WWW 2014)\n\n* **[Label Propagation](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.label_propagation.LabelPropagation)** from Raghavan *et al.*: [Near Linear Time Algorithm to Detect Community Structures in Large-Scale Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F0709.2938) (Physics Review E 2007)\n\n\n**Proximity Preserving Node Embedding**\n\n* **[GraRep](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.grarep.GraRep)** from Cao *et al.*: [GraRep: Learning Graph Representations with Global Structural Information](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=2806512) (CIKM 2015)\n\n* **[DeepWalk](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.deepwalk.DeepWalk)** from Perozzi *et al.*: [DeepWalk: Online Learning of Social Representations](https:\u002F\u002Farxiv.org\u002Fabs\u002F1403.6652) (KDD 2014)\n\n* **[Node2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.node2vec.Node2Vec)** from Grover *et al.*: [node2vec: Scalable Feature Learning for Networks](https:\u002F\u002Fcs.stanford.edu\u002F~jure\u002Fpubs\u002Fnode2vec-kdd16.pdf) (KDD 2016)\n\n* **[SocioDim](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.sociodim.SocioDim)** from Tang *et al.*: [Relational Learning via Latent Social Dimensions](ttp:\u002F\u002Fwww.public.asu.edu\u002F~huanliu\u002Fpapers\u002Fkdd09.pdf) (KDD 2009)\n\n* **[GLEE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.geometriclaplacianeigenmaps.GLEE)** from Torres *et al.*: [GLEE: Geometric Laplacian Eigenmap Embedding](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09763) (Journal of Complex Networks 2020)\n\n* **[BoostNE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.boostne.BoostNE)** from Li *et al.*: [Multi-Level Network Embedding with Boosted Low-Rank Matrix Approximation](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.08627) (ASONAM 2019)\n\n* **[NodeSketch](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.nodesketch.NodeSketch)**  from Yang *et al.*: [NodeSketch: Highly-Efficient Graph Embeddings via Recursive Sketching](https:\u002F\u002Fexascale.info\u002Fassets\u002Fpdf\u002Fyang2019nodesketch.pdf) (KDD 2019)\n\n* **[Diff2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.diff2vec.Diff2Vec)** from Rozemberczki and Sarkar: [Fast Sequence Based Embedding with Diffusion Graphs](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.07463) (CompleNet 2018)\n\n* **[NetMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.netmf.NetMF)** from Qiu *et al.*: [Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and Node2Vec](https:\u002F\u002Fkeg.cs.tsinghua.edu.cn\u002Fjietang\u002Fpublications\u002FWSDM18-Qiu-et-al-NetMF-network-embedding.pdf) (WSDM 2018)\n\n* **[RandNE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.randne.RandNE)** from Zhang *et al.*: [Billion-scale Network Embedding with Iterative Random Projection](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.02396) (ICDM 2018)\n\n* **[Walklets](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.walklets.Walklets)** from Perozzi *et al.*: [Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings](https:\u002F\u002Farxiv.org\u002Fabs\u002F1605.02115) (ASONAM 2017)\n\n* **[HOPE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.hope.HOPE)** from Ou *et al.*: [Asymmetric Transitivity Preserving Graph Embedding](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F2939672.2939751) (KDD 2016)\n\n* **[NMF-ADMM](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.nmfadmm.NMFADMM)** from Sun and Févotte: [Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence](http:\u002F\u002Fstatweb.stanford.edu\u002F~dlsun\u002Fpapers\u002Fnmf_admm.pdf) (ICASSP 2014)\n\n* **[Laplacian Eigenmaps](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.laplacianeigenmaps.LaplacianEigenmaps)** from Belkin and Niyogi: [Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F1961-laplacian-eigenmaps-and-spectral-techniques-for-embedding-and-clustering) (NIPS 2001)\n\n**Structural Node Level Embedding**\n\n* **[GraphWave](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.structural.graphwave.GraphWave)** from Donnat *et al.*: [Learning Structural Node Embeddings via Diffusion Wavelets](https:\u002F\u002Farxiv.org\u002Fabs\u002F1710.10321) (KDD 2018)\n\n* **[Role2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.structural.role2vec.Role2vec)** from Ahmed *et al.*: [Learning Role-based Graph Embeddings](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.02896) (IJCAI StarAI 2018)\n\n**Attributed Node Level Embedding**\n\n* **[FEATHER-N](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.feathernode.FeatherNode)** from Rozemberczki *et al.*: [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.07959) (CIKM 2020)\n\n* **[TADW](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.tadw.TADW)** from Yang *et al.*: [Network Representation Learning with Rich Text Information](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F15\u002FPapers\u002F299.pdf) (IJCAI 2015)\n\n* **[MUSAE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.musae.MUSAE)** from Rozemberczki *et al.*: [Multi-Scale Attributed Node Embedding](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.13021) (Arxiv 2019)\n\n* **[AE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.ae.AE)** from Rozemberczki *et al.*: [Multi-Scale Attributed Node Embedding](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.13021) (Arxiv 2019)\n\n* **[FSCNMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.fscnmf.FSCNMF)** from Bandyopadhyay *et al.*: [Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1804.05313.pdf) (ArXiV 2018)\n\n* **[SINE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.sine.SINE)** from Zhang *et al.*: [SINE: Scalable Incomplete Network Embedding](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.06768.pdf) (ICDM 2018)\n\n* **[BANE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.bane.BANE)** from Yang *et al.*: [Binarized Attributed Network Embedding](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8626170) (ICDM 2018)\n\n* **[TENE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.tene.TENE)** from Yang *et al.*: [Enhanced Network Embedding with Text Information](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8545577) (ICPR 2018)\n\n* **[ASNE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.asne.ASNE)** from Liao *et al.*: [Attributed Social Network Embedding](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.04969) (TKDE 2018)\n\n**Meta Node Embedding**\n\n* **[NEU](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.meta.neu.NEU)** from Yang *et al.*: [Fast Network Embedding Enhancement via High Order Proximity Approximation](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2017\u002F0544.pdf) (IJCAI 2017)\n\n**Graph Level Embedding**\n\n* **[FEATHER-G](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.feathergraph.FeatherGraph)** from Rozemberczki *et al.*: [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.07959) (CIKM 2020)\n\n* **[Graph2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.graph2vec.Graph2Vec)** from Narayanan *et al.*: [Graph2Vec: Learning Distributed Representations of Graphs](https:\u002F\u002Farxiv.org\u002Fabs\u002F1707.05005) (MLGWorkshop 2017)\n\n* **[NetLSD](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.netlsd.NetLSD)** from Tsitsulin *et al.*: [NetLSD: Hearing the Shape of a Graph](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.10712) (KDD 2018)\n\n* **[WaveletCharacteristic](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.waveletcharacteristic.WaveletCharacteristic)** from Wang *et al.*: [Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.07016) (CIKM 2021)\n\n* **[IGE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.ige.IGE)** from Galland *et al.*: [Invariant Embedding for Graph Classification](https:\u002F\u002Fgraphreason.github.io\u002Fpapers\u002F16.pdf) (ICML 2019 LRGSD Workshop)\n\n* **[LDP](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.ldp.LDP)** from Cai *et al.*: [A Simple Yet Effective Baseline for Non-Attributed Graph Classification](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.03508) (ICLR 2019)\n\n* **[GeoScattering](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.geoscattering.GeoScattering)** from Gao *et al.*: [Geometric Scattering for Graph Data Analysis](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fgao19e.html) (ICML 2019)\n\n* **[GL2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.gl2vec.GL2Vec)** from Chen and Koga: [GL2Vec: Graph Embedding Enriched by Line Graphs with Edge Features](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-36718-3_1) (ICONIP 2019)\n\n* **[SF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.sf.SF)** from de Lara and Pineau: [A Simple Baseline Algorithm for Graph Classification](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.09155) (NeurIPS RRL Workshop 2018)\n\n* **[FGSD](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.fgsd.FGSD)** from Verma and Zhang: [Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F6614-hunt-for-the-unique-stable-sparse-and-fast-feature-learning-on-graphs.pdf) (NeurIPS 2017)\n\nHead over to our [documentation](https:\u002F\u002Fkarateclub.readthedocs.io) to find out more about installation and data handling, a full list of implemented methods, and datasets. For a quick start, check out our [examples](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Ftree\u002Fmaster\u002Fexamples.py).\n\nIf you notice anything unexpected, please open an [issue](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues) and let us know. If you are missing a specific method, feel free to open a [feature request](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues).\nWe are motivated to constantly make Karate Club even better.\n\n\n--------------------------------------------------------------------------------\n\n**Installation**\n\nKarate Club can be installed with the following pip command.\n\n```sh\n$ pip install karateclub\n```\n\nAs we create new releases frequently, upgrading the package casually might be beneficial.\n\n```sh\n$ pip install karateclub --upgrade\n```\n\n--------------------------------------------------------------------------------\n\n**Running examples**\n\nAs part of the documentation we provide a number of use cases to show how the clusterings and embeddings can be utilized for downstream learning. These can accessed [here](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fnotes\u002Fintroduction.html) with detailed line-by-line explanations.\n\n\nBesides the case studies we provide synthetic examples for each model. These can be tried out by running the example scripts. In order to run one of the examples, the Graph2Vec snippet:\n\n```sh\n$ cd examples\u002Fwhole_graph_embedding\u002F\n$ python graph2vec_example.py\n```\n\n--------------------------------------------------------------------------------\n\n**Running tests**\n\nFrom the project's root-level directory:\n\n```sh\n$ pytest\n```\n\n--------------------------------------------------------------------------------\n\n**License**\n\n- [GNU General Public License v3.0](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fblob\u002Fmaster\u002FLICENSE)\n","![版本](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fkarateclub.svg?style=plastic)\n![许可证](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fbenedekrozemberczki\u002Fkarateclub.svg)\n[![仓库大小](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frepo-size\u002Fbenedekrozemberczki\u002Fkarateclub.svg)](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Farchive\u002Fmaster.zip)\n[![Arxiv](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FArXiv-2003.04819-orange.svg)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.04819)\n[![构建徽章](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fworkflows\u002FCI\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Factions?query=workflow%3ACI)\n[![覆盖率徽章](https:\u002F\u002Fcodecov.io\u002Fgh\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fbranch\u002Fmaster\u002Fgraph\u002Fbadge.svg)](https:\u002F\u002Fcodecov.io\u002Fgithub\u002Fbenedekrozemberczki\u002Fkarateclub?branch=master)\n\u003Cp align=\"center\">\n  \u003Cimg width=\"90%\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fbenedekrozemberczki_karateclub_readme_ca8cd60f8845.jpg\" \u002F>\n\u003C\u002Fp>\n\n------------------------------------------------------\n\n\n**Karate Club** 是一个面向 [NetworkX](https:\u002F\u002Fnetworkx.github.io\u002F) 的无监督机器学习扩展库。\n\n请访问 **[文档](https:\u002F\u002Fkarateclub.readthedocs.io\u002F)**、相关 **[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.04819)**、**[宣传视频](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=t212-ntxu2U)**，以及 **[外部资源](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fnotes\u002Fresources.html)**。\n\n*Karate Club* 汇集了用于在图结构数据上进行无监督学习的前沿方法。简单来说，它就像一把瑞士军刀，专为小规模图挖掘研究而设计。首先，它提供了节点级和图级的网络嵌入技术；其次，它还包含多种重叠与非重叠的社区检测方法。所实现的方法覆盖了广泛的网络科学领域（如 [NetSci](https:\u002F\u002Fnetscisociety.net\u002Fhome)、[Complenet](https:\u002F\u002Fcomplenet.weebly.com\u002F)）、数据挖掘（如 [ICDM](http:\u002F\u002Ficdm2019.bigke.org\u002F)、[CIKM](http:\u002F\u002Fwww.cikm2019.net\u002F)、[KDD](https:\u002F\u002Fwww.kdd.org\u002Fkdd2020\u002F)）、人工智能（如 [AAAI](http:\u002F\u002Fwww.aaai.org\u002FConferences\u002Fconferences.php)、[IJCAI](https:\u002F\u002Fwww.ijcai.org\u002F)）以及机器学习（如 [NeurIPS](https:\u002F\u002Fnips.cc\u002F)、[ICML](https:\u002F\u002Ficml.cc\u002F)、[ICLR](https:\u002F\u002Ficlr.cc\u002F)）等领域的会议、研讨会和知名期刊中的相关研究成果。\n\n新近推出的图分类数据集已上线至 [SNAP](https:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002F#disjointgraphs)、[TUD 图像核数据集](https:\u002F\u002Fls11-www.cs.tu-dortmund.de\u002Fstaff\u002Fmorris\u002Fgraphkerneldatasets) 和 [GraphLearning.io](https:\u002F\u002Fchrsmrrs.github.io\u002Fdatasets\u002F)。\n\n--------------------------------------------------------------\n\n**引用**\n\n如果您在研究中发现 *Karate Club* 及其新数据集非常有用，请考虑引用以下论文：\n\n```bibtex\n@inproceedings{karateclub,\n       title = {{Karate Club: 一个以 API 为导向的开源 Python 框架，用于图上的无监督学习}},\n       author = {Benedek Rozemberczki、Oliver Kiss、Rik Sarkar},\n       year = {2020},\n       pages = {3125–3132},\n       booktitle = {29th ACM International Conference on Information and Knowledge Management (CIKM '20) 的会议论文集},\n       organization = {ACM},\n}\n```\n----------------------------------------------------------------\n\n**一个简单的示例**\n\n*Karate Club* 让现代社区检测技术的使用变得极为便捷（详见 [此处](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fnotes\u002Fintroduction.html) 的配套教程）。例如，只需几行代码，您就可以在 Watts-Strogatz 图上使用该库 [Ego 分裂](https:\u002F\u002Fwww.eecs.yorku.ca\u002Fcourse_archive\u002F2017-18\u002FF\u002F6412\u002Freading\u002Fkdd17p145.pdf)：\n\n```python\nimport networkx as nx\nfrom karateclub import EgoNetSplitter\n\ng = nx.newman_watts_strogatz_graph(1000, 20, 0.05)\n\nsplitter = EgoNetSplitter(1.0)\n\nsplitter.fit(g)\n\nprint(splitter.get_memberships())\n```\n\n----------------------------------------------------------------\n\n**包含的模型**\n\n具体而言，我们实现了以下社区检测与嵌入方法：\n\n**重叠社区检测**\n\n* **[DANMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.danmf.DANMF)** 来自 Ye 等人：[基于深度自动编码器的非负矩阵分解法用于社区检测](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002FDANMF\u002Fblob\u002Fmaster\u002F18DANMF.pdf)（CIKM 2018）\n\n* **[M-NMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.mnmf.M_NMF)** 来自 Wang 等人：[社区保持的网络嵌入](https:\u002F\u002Faaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI17\u002Fpaper\u002Fview\u002F14589)（AAAI 2017）\n\n* **[Ego 分裂](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.ego_splitter.EgoNetSplitter)** 来自 Epasto 等人：[Ego 分裂框架：从非重叠到重叠聚类](https:\u002F\u002Fwww.eecs.yorku.ca\u002Fcourse_archive\u002F2017-18\u002FF\u002F6412\u002Freading\u002Fkdd17p145.pdf)（KDD 2017）\n\n* **[NNSED](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.nnsed.NNSED)** 来自 Sun 等人：[一种非负对称编码器-解码器方法用于社区检测](http:\u002F\u002Fwww.bigdatalab.ac.cn\u002F~shenhuawei\u002Fpublications\u002F2017\u002Fcikm-sun.pdf)（CIKM 2017）\n\n* **[BigClam](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.bigclam.BigClam)** 来自 Yang 和 Leskovec：[大规模的重叠社区检测：一种非负矩阵分解方法](http:\u002F\u002Finfolab.stanford.edu\u002F~crucis\u002Fpubs\u002Fpaper-nmfagm.pdf)（WSDM 2013）\n\n* **[SymmNMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.overlapping.symmnmf.SymmNMF)** 来自 Kuang 等人：[用于图聚类的对称非负矩阵分解](https:\u002F\u002Fwww.cc.gatech.edu\u002F~hpark\u002Fpapers\u002FDaDingParkSDM12.pdf)（SDM 2012）\n\n**非重叠社区检测**\n\n* **[GEMSEC](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.gemsec.GEMSEC)** 来自 Rozemberczki 等人：[GEMSEC：带有自聚类的图嵌入](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.03997)（ASONAM 2019）\n\n* **[EdMot](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.edmot.EdMot)** 来自 Li 等人：[EdMot：一种针对模式感知社区检测的边缘增强方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04560)（KDD 2019）\n\n* **[SCD](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.scd.SCD)** 来自 Prat-Perez 等人：[高质量、可扩展且并行的大型真实图社区检测](http:\u002F\u002Fwwwconference.org\u002Fproceedings\u002Fwww2014\u002Fproceedings\u002Fp225.pdf)（WWW 2014）\n\n* **[标签传播](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.community_detection.non_overlapping.label_propagation.LabelPropagation)**——出自 Raghavan 等人：《用于大规模网络社区结构检测的近线性时间算法》（ArXiv 2007）\n\n\n**保持邻近度的节点嵌入**\n\n* **[GraRep](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.grarep.GraRep)**——出自 Cao 等人：《GraRep：利用全局结构信息学习图表示》（CIKM 2015）\n* **[DeepWalk](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.deepwalk.DeepWalk)**——出自 Perozzi 等人：《DeepWalk：在线学习社交表示》（ArXiv 2014）\n* **[Node2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.node2vec.Node2Vec)**——出自 Grover 等人：《node2vec：面向网络的可扩展特征学习》（CS.斯坦福大学，Jietang，2016）\n* **[SocioDim](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.sociodim.SocioDim)**——出自 Tang 等人：《基于潜在社会维度的关系学习》（KDD 2009）\n* **[GLEE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.geometriclaplacianeigenmaps.GLEE)**——出自 Torres 等人：《GLEE：几何拉普拉斯特征映射嵌入》（Journal of Complex Networks 2020）\n* **[BoostNE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.boostne.BoostNE)**——出自 Li 等人：《基于提升的低秩矩阵近似实现的多级网络嵌入》（ASONAM 2019）\n* **[NodeSketch](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.nodesketch.NodeSketch)**——出自 Yang 等人：《NodeSketch：通过递归抽样实现高效图嵌入》（Exascale 信息，2019）\n* **[Diff2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.diff2vec.Diff2Vec)**——出自 Rozemberczki 和 Sarkar：《基于扩散图的快速序列嵌入》（CompleNet 2018）\n* **[NetMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.netmf.NetMF)**——出自 Qiu 等人：《将网络嵌入视为矩阵分解：统一 DeepWalk、LINE、PTE 与 Node2Vec》（WSDM 2018）\n* **[RandNE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.randne.RandNE)**——出自 Zhang 等人：《基于迭代随机投影的数十亿规模网络嵌入》（ArXiv 2018）\n* **[Walklets](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.walklets.Walklets)**——出自 Perozzi 等人：《别走路，跳过！在线学习多尺度网络嵌入》（ArXiv 2016）\n* **[HOPE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.hope.HOPE)**——出自 Ou 等人：《非对称传递性保持的图嵌入》（DLACM 2016）\n* **[NMF-ADMM](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.nmfadmm.NMFADMM)**——出自 Sun 和 Févotte：《用于非负矩阵分解的交替方向乘法器方法：结合贝塔散度》（ICASSP 2014）\n* **[拉普拉斯特征映射](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.neighbourhood.laplacianeigenmaps.LaplacianEigenmaps)**——出自 Belkin 和 Niyogi：《拉普拉斯特征映射与谱技术：用于嵌入与聚类》（NIPS 2001）\n\n**结构化节点层级嵌入**\n\n* **[GraphWave](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.structural.graphwave.GraphWave)**——出自 Donnat 等人：《通过扩散小波学习结构化节点嵌入》（KDD 2018）\n* **[Role2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.structural.role2vec.Role2vec)**——出自 Ahmed 等人：《学习基于角色的图嵌入》（ArXiv 2018）\n\n**带属性的节点层级嵌入**\n\n* **[FEATHER-N](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.feathernode.FeatherNode)**——出自 Rozemberczki 等人：《图上的特征函数：从统计描述符到参数化模型——如“鸟群”一般》（ArXiv 2020）\n* **[TADW](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.tadw.TADW)**——出自 Yang 等人：《利用丰富文本信息进行网络表示学习》（IJCAI StarAI 2015）\n* **[MUSAE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.musae.MUSAE)**——出自 Rozemberczki 等人：《多尺度带属性节点嵌入》（ArXiv 2019）\n* **[AE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.ae.AE)**——出自 Rozemberczki 等人：《多尺度带属性节点嵌入》（ArXiv 2019）\n* **[FSCNMF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.fscnmf.FSCNMF)**——出自 Bandyopadhyay 等人：《通过非负矩阵分解融合结构与内容，实现信息网络的嵌入》（ArXiV 2018）\n* **[SINE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.sine.SINE)**——出自 Zhang 等人：《SINE：可扩展的不完整网络嵌入》（ArXiv 2018）\n* **[BANE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.bane.BANE)**——出自 Yang 等人：《二值化带属性网络嵌入》（IEEExplore.ieee.org，8626170）（ICDM 2018）\n\n* **[TENE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.tene.TENE)** 由杨等人提出：[利用文本信息增强网络嵌入](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8545577)（ICPR 2018）\n\n* **[ASNE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.attributed.asne.ASNE)** 由廖等人提出：[带属性的社会网络嵌入](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.04969)（TKDE 2018）\n\n**元节点嵌入**\n\n* **[NEU](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.node_embedding.meta.neu.NEU)** 由杨等人提出：[通过高阶邻近度近似实现的快速网络嵌入增强](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F2017\u002F0544.pdf)（IJCAI 2017）\n\n**图级嵌入**\n\n* **[FEATHER-G](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.feathergraph.FeatherGraph)** 由罗赞伯奇基等人提出：[图上的特征函数：从统计描述符到参数化模型——“鸟群”式特征](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.07959)（CIKM 2020）\n\n* **[Graph2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.graph2vec.Graph2Vec)** 由纳拉亚南等人提出：[Graph2Vec：学习图的分布式表示](https:\u002F\u002Farxiv.org\u002Fabs\u002F1707.05005)（MLG Workshop 2017）\n\n* **[NetLSD](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.netlsd.NetLSD)** 由齐楚林等人提出：[NetLSD：倾听图的形状](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.10712)（KDD 2018）\n\n* **[WaveletCharacteristic](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.waveletcharacteristic.WaveletCharacteristic)** 由王等人提出：[基于扩散-小波的图节点特征分布表征的图嵌入](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.07016)（CIKM 2021）\n\n* **[IGE](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.ige.IGE)** 由加兰德等人提出：[用于图分类的不变性嵌入](https:\u002F\u002Fgraphreason.github.io\u002Fpapers\u002F16.pdf)（ICML 2019 LRGSD 工作坊）\n\n* **[LDP](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.ldp.LDP)** 由蔡等人提出：[一种简单而有效的非属性图分类基准](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.03508)（ICLR 2019）\n\n* **[GeoScattering](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.geoscattering.GeoScattering)** 由高等人提出：[用于图数据分析的几何散射方法](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fgao19e.html)（ICML 2019）\n\n* **[GL2Vec](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.gl2vec.GL2Vec)** 由陈和古贺提出：[GL2Vec：通过带有边特征的线性图丰富图嵌入](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-36718-3_1)（ICONIP 2019）\n\n* **[SF](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.sf.SF)** 由德拉拉和皮诺提出：[一种用于图分类的简单基准算法](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.09155)（NeurIPS RRL 工作坊 2018）\n\n* **[FGSD](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fmodules\u002Froot.html#karateclub.graph_embedding.fgsd.FGSD)** 由维尔玛和张提出：[在图上进行独特、稳定、稀疏且快速的特征学习的猎手](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F6614-hunt-for-the-unique-stable-sparse-and-fast-feature-learning-on-graphs.pdf)（NeurIPS 2017）\n\n前往我们的[文档](https:\u002F\u002Fkarateclub.readthedocs.io)，了解有关安装与数据处理的更多详情，以及已实现的方法和数据集的完整列表。如需快速入门，请查看我们的[示例](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Ftree\u002Fmaster\u002Fexamples.py)。\n\n若发现任何意外情况，请随时打开[问题](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues)并告知我们。如果您缺少某项特定方法，欢迎随时提交[功能请求](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues)。\n我们始终致力于让 Karate Club 不断臻于完善。\n\n--------------------------------------------------------------------------------\n\n**安装**\n\nKarate Club 可以通过以下 pip 命令进行安装。\n\n```sh\n$ pip install karateclub\n```\n\n由于我们经常发布新版本，因此适时升级软件包可能会带来诸多益处。\n\n```sh\n$ pip install karateclub --upgrade\n```\n\n--------------------------------------------------------------------------------\n\n**运行示例**\n\n作为文档的一部分，我们提供了多种用例，展示如何将聚类结果与嵌入向量应用于下游学习任务。这些用例可[在此](https:\u002F\u002Fkarateclub.readthedocs.io\u002Fen\u002Flatest\u002Fnotes\u002Fintroduction.html)查阅，并附有详细的逐行说明。\n\n除了案例研究之外，我们还为每种模型提供了合成示例。您只需运行示例脚本即可尝试这些示例。要运行其中某个示例，您可以使用 Graph2Vec 的代码片段：\n\n```sh\n$ cd examples\u002Fwhole_graph_embedding\u002F\n$ python graph2vec_example.py\n```\n\n--------------------------------------------------------------------------------\n\n**运行测试**\n\n在项目根目录下：\n\n```sh\n$ pytest\n```\n\n--------------------------------------------------------------------------------\n\n**许可证**\n\n- [GNU 通用公共许可证 v3.0](https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fblob\u002Fmaster\u002FLICENSE)","# Karate Club 快速上手指南\n\n## 环境准备\n- **系统要求**：Python 3.6+，支持 Linux \u002F macOS \u002F Windows  \n- **前置依赖**：  \n  - NetworkX ≥ 2.3  \n  - NumPy ≥ 1.17  \n  - SciPy ≥ 1.3  \n  - scikit-learn ≥ 0.22  \n\n## 安装步骤\n```bash\n# 1. 创建并激活虚拟环境（可选）\npython -m venv karate_env\nsource karate_env\u002Fbin\u002Factivate  # Windows 用 karate_env\\Scripts\\activate\n\n# 2. 使用国内镜像加速安装\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple karateclub\n```\n\n## 基本使用\n```python\nimport networkx as nx\nfrom karateclub import EgoNetSplitter\n\n# 1. 构造或加载图\ng = nx.newman_watts_strogatz_graph(1000, 20, 0.05)\n\n# 2. 初始化模型\nsplitter = EgoNetSplitter(1.0)\n\n# 3. 训练并获取结果\nsplitter.fit(g)\nmemberships = splitter.get_memberships()\nprint(memberships)\n```\n\n完成！如需更多示例，参考 [官方文档](https:\u002F\u002Fkarateclub.readthedocs.io\u002F)。","一家中型电商公司想从 200 万用户的“浏览-加购-分享”行为图中找出潜在高价值社群，以便做精准营销。数据科学团队只有 3 人，且对图算法经验有限。\n\n### 没有 karateclub 时\n- 需要手动实现 DeepWalk、Node2Vec 等 10 余种嵌入算法，代码量上千行，调试耗时 2 周。  \n- 社区检测用 Louvain 时，发现重叠社群无法处理，只得再写一套 Ego-splitting，结果又花 3 天。  \n- 不同算法输出格式各异，后续聚类、可视化全靠脚本拼接，维护噩梦。  \n- 线上 A\u002FB 测试时，因模型更新慢，错过双 11 预热期，损失预估 80 万 GMV。\n\n### 使用 karateclub 后\n- 3 行代码调用 `DeepWalk` + `EgoNetSplitter`，30 分钟完成节点嵌入与重叠社群划分，直接输出统一字典格式。  \n- 内置 30+ 模型一键切换，团队用 `GEMSEC` 试出更紧密的“高客单价”社群，准确率提升 12%。  \n- 结果无缝对接 scikit-learn 与 NetworkX，可视化脚本复用率 100%，维护成本归零。  \n- 模型迭代周期从 2 周压缩到 1 天，赶在双 11 前上线，额外带来 120 万 GMV。\n\nkarateclub 把图上的无监督学习变成“调包即用”，让小团队也能像大厂一样快速挖掘社群价值。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fbenedekrozemberczki_karateclub_8f83d238.png","benedekrozemberczki","Benedek Rozemberczki","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fbenedekrozemberczki_4cc882ba.png","Machine Learning Research Scientist at Google| PhD from The University of Edinburgh.","@google","United Kingdom","benedek.rozemberczki@gmail.com","benrozemberczki",null,"https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki",[86],{"name":87,"color":88,"percentage":89},"Python","#3572A5",100,2276,257,"2026-04-04T20:11:23","GPL-3.0",1,"Linux, macOS, Windows","未说明",{"notes":98,"python":99,"dependencies":100},"纯 CPU 实现，无需 GPU；安装仅需 pip install karateclub；所有算法针对小规模图数据设计，内存占用随图规模线性增长","3.6+",[101,102,103,104,105,106,107,108],"networkx","numpy","scipy","scikit-learn","tqdm","gensim","numba","pandas",[54,13],[111,112,113,101,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"community-detection","graph-clustering","deepwalk","louvain","network-science","machine-learning","unsupervised-learning","gcn","node2vec","graph2vec","supervised-learning","sklearn","networkx-graph","scikit","label-propagation","graph-embedding","network-embedding","node-embedding","2vec","2026-03-27T02:49:30.150509","2026-04-06T08:47:03.405912",[133,138,143,148,153,158],{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},6252,"如何降低 numpy \u002F networkx \u002F pandas 的版本要求，避免与其他库冲突？","维护者已在 #133 中放宽了依赖版本限制，升级到最新版 karateclub 即可兼容较新的 numpy、networkx 和 pandas。若仍有问题，可先 `pip install pandas numpy -U` 再安装 karateclub。","https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues\u002F133",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},6253,"运行 GL2vec 时出现 “RuntimeError: you must first build vocabulary before training the model” 怎么办？","该错误通常是因为输入给 GL2vec 的是单个图而非图列表。请把多个 NetworkX 图放进一个 Python list 再调用 `.fit([graph1, graph2, ...])`，不要逐张图单独训练。","https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues\u002F27",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},6254,"出现 “RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xf” 怎么解决？","这是二进制扩展与 numpy 版本不匹配导致的。建议：1) 新建 Python 3.10 虚拟环境；2) 先 `pip install pandas numpy -U` 升级 numpy；3) 再 `pip install karateclub`。Ubuntu 用户同样适用。","https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues\u002F142",{"id":149,"question_zh":150,"answer_zh":151,"source_url":152},6255,"如何从零开始构建自己的图数据集并生成图嵌入？","使用 NetworkX 构建图即可：\n```python\nimport networkx as nx\nG = nx.Graph()\nG.add_nodes_from([0, 1, 2])\nG.add_edges_from([(0,1), (1,2)])\n# 设置节点特征（可选）\nfor n in G.nodes:\n    G.nodes[n]['feature'] = [1.0, 2.0]\ngraphs = [G]  # 图级嵌入需要图列表\nfrom karateclub import Graph2Vec\nmodel = Graph2Vec()\nmodel.fit(graphs)\nembeddings = model.get_embedding()\n```\n节点索引必须从 0 开始且连续，无孤立节点。","https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues\u002F101",{"id":154,"question_zh":155,"answer_zh":156,"source_url":157},6256,"Feather-Graph 能否利用节点属性？如何扩展？","官方 Feather-Graph 默认只用对数度和聚类系数作为节点特征。若想利用节点属性，可把 Feather-Node 的特征生成逻辑嫁接到 Feather-Graph：先为每个图构造节点属性矩阵，再按 Feather-Node 的方式做 T-SVD，最后把得到的节点特征做池化得到整图向量。注意整个数据集需一次性做 T-SVD，新图用同一组基投影。","https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues\u002F125",{"id":159,"question_zh":160,"answer_zh":161,"source_url":162},6257,"GL2vec 的实现是否遗漏了原论文中的关键步骤？","是的。原论文将原图嵌入与线图嵌入拼接后得到最终向量（Graph + Line graph → vector）。当前实现只返回线图嵌入，且忽略了原图的边属性，导致性能下降。建议自行拼接两种嵌入，并在下游任务中验证：concat(G, LG) 通常优于单独使用 G 或 LG。","https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fissues\u002F5",[164,169,174,179,184,189,194,199,204,209,214,219,224,229,234,239,244,249,254,259],{"id":165,"version":166,"summary_zh":167,"released_at":168},115510,"v_10304","## What's Changed\r\n* Modify test statement to use pytest in lieu of setuptools. by @WhatTheFuzz in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F119\r\n* Update requirements to modern versions. by @WhatTheFuzz in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F120\r\n\r\n## New Contributors\r\n* @WhatTheFuzz made their first contribution in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F119\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fcompare\u002Fv_10303...v_10304","2022-12-04T19:04:05",{"id":170,"version":171,"summary_zh":172,"released_at":173},115511,"v_10303","## What's Changed\r\n* Implemented first & second-order LINE by @LucaCappelletti94 in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F114\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fcompare\u002Fv_10302...v_10303","2022-10-22T13:36:23",{"id":175,"version":176,"summary_zh":177,"released_at":178},115512,"v_10302","## What's Changed\r\n* Replaced fullargsspec with signature, as it broke in my system by @LucaCappelletti94 in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F111\r\n* Add get_params method to BaseEstimator by @tomlincr in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F112\r\n\r\n## New Contributors\r\n* @tomlincr made their first contribution in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F112\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fcompare\u002Fv_10301...v_10302","2022-09-04T19:42:28",{"id":180,"version":181,"summary_zh":182,"released_at":183},115513,"v_10301","## What's Changed\r\n* docs: Fix a few typos by @timgates42 in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F104\r\n* Exposed parameter `maximum_number_of_iterations` by @LucaCappelletti94 in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F106\r\n* Pyre type error fixed. by @luca-digrazia in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F108\r\n* Resolved compatibility issue with sklearn in BoostNE by @LucaCappelletti94 in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F107\r\n\r\n## New Contributors\r\n* @luca-digrazia made their first contribution in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F108\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fcompare\u002Fv_10300...v_10301","2022-08-13T14:08:23",{"id":185,"version":186,"summary_zh":187,"released_at":188},115514,"v_10300","The release adds vector induction (inference) for all of the graph level embedding methods. Including:\r\n\r\nGraph2Vec\r\nGL2Vec","2022-06-04T20:12:40",{"id":190,"version":191,"summary_zh":192,"released_at":193},115515,"v_10204","## What's Changed\r\n\r\n* NetworkX version fixed to \u003C2.7 - scipy sparse version change.\r\n* Just fixed some warning of upcoming dropped features by @LucaCappelletti94 in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F93\r\n\r\n## New Contributors\r\n* @LucaCappelletti94 made their first contribution in https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fpull\u002F93\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fcompare\u002Fv_10203...v_10204","2022-06-03T13:04:02",{"id":195,"version":196,"summary_zh":197,"released_at":198},115516,"v_10203","**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbenedekrozemberczki\u002Fkarateclub\u002Fcompare\u002Fv_10202...v_10203","2022-01-22T19:35:55",{"id":200,"version":201,"summary_zh":202,"released_at":203},115517,"v_10202","Added Wavelet Characteristic from the CIKM 2021 paper: Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization","2021-09-29T21:05:51",{"id":205,"version":206,"summary_zh":207,"released_at":208},115518,"v_10201","- Weighted FEATHER algorithm.","2021-08-04T20:14:06",{"id":210,"version":211,"summary_zh":212,"released_at":213},115519,"v_10200","The new release supports directed and disjoint graphs:\r\n\r\n- Directed graph support.\r\n- Disjoint graph support.","2021-07-02T18:00:48",{"id":215,"version":216,"summary_zh":217,"released_at":218},115520,"v_10100","- Allows higher version of gensim.","2021-05-19T21:53:35",{"id":220,"version":221,"summary_zh":222,"released_at":223},115521,"v_10024","- Added flag.","2021-03-30T00:11:09",{"id":225,"version":226,"summary_zh":227,"released_at":228},115522,"v_10023","Release SocioDim.","2021-01-25T18:14:21",{"id":230,"version":231,"summary_zh":232,"released_at":233},115523,"v_10022","Increased vector count.","2020-12-01T21:11:27",{"id":235,"version":236,"summary_zh":237,"released_at":238},115524,"v_10020","- Added RandomNE","2020-11-20T16:49:51",{"id":240,"version":241,"summary_zh":242,"released_at":243},115525,"v_100021","- Added LDP","2020-11-20T20:30:46",{"id":245,"version":246,"summary_zh":247,"released_at":248},115526,"v_10019","Fixing the M-NMF.","2020-11-06T20:45:53",{"id":250,"version":251,"summary_zh":252,"released_at":253},115527,"v_100018","- Noise parameter added.","2020-11-05T12:16:09",{"id":255,"version":256,"summary_zh":257,"released_at":258},115528,"v_10017","Added the AE dataset","2020-10-23T10:01:15",{"id":260,"version":261,"summary_zh":262,"released_at":263},115529,"v_10016","Added GLEE","2020-10-18T16:25:37"]