Awesome-Deep-Community-Detection

Awesome-Deep-Community-Detection

社区发现中的深度学习方法综述与资源集

本项目汇集了深度学习在社区发现领域的最新研究成果和资源。内容包括综述论文、基于卷积网络、图注意力网络和生成对抗网络的方法,以及相关数据集和工具。同时收录了传统的非深度学习社区发现技术,为研究人员提供全面参考。项目整理了大量论文、代码实现和相关资源,是了解该研究前沿的重要参考。

社区检测深度学习图神经网络网络嵌入复杂网络Github开源项目

Awesome Deep Community Detection

Awesome PRs Welcome GitHub stars GitHub forks

A collection of papers, implementations, datasets, and tools for deep and non-deep community detection.


Traditional Methods VS. Deep Learninig-based Methods

taxonomy


A Timeline of Community Detection Development

timeline


Survey

Paper TitleVenueYearMaterials
A comprehensive survey on community detection with deep learningIEEE TNNLS2022[Paper] <br> [Report] <br> [Supplementary]
A survey of community detection approaches: From statistical modeling to deep learningIEEE TKDE2021[Paper]
Deep learning for community detection: Progress, challenges and opportunitiesIJCAI2020[Paper] <br>[Report]
A survey of community detection methods in multilayer networksData Min. Knowl. Discov.2020[Paper]
Community detection in node-attributed social networks: A surveyComput. Sci. Rev.2020[Paper]
Community detection in networks: A multidisciplinary reviewJ. Netw. Comput. Appl.2018[Paper]
Community discovery in dynamic networks: A surveyACM Comput. Surv.2018[Paper]
Evolutionary computation for community detection in networks: A reviewIEEE TEVC2018[Paper]
Metrics for community analysis: A surveyACM Comput. Surv.2017[Paper]
Network community detection: A review and visual surveyPreprint2017[Paper]
Community detection in networks: A user guidePhys. Rep.2016[Paper]
Community detection in social networksWIREs Data Min. Knowl. Discov.2016[Paper]
Overlapping community detection in networks: The state-of-the-art and comparative studyACM Comput. Surv.2013[Paper]
Clustering and community detection in directed networks: A surveyPhys. Rep.2013[Paper]
Community detection in graphsPhys. Rep.2010[Paper]

Convolutional Networks-based Community Detection

CNN-based Community Detection

Paper TitleVenueYearMethodMaterials
Inductive representation learning via CNN for partially-unseen attributed networksIEEE TNSE2021IEPAN[Paper]
A deep learning approach for semi-supervised community detection in online social networksKnowl.-Based Syst.2021SparseConv2D[Paper]
Edge classification based on convolutional neural networks for community detection in complex networkPhysica A2020ComNet-R[Paper]
A deep learning based community detection approachSAC2019SparseConv[Paper]
Deep community detection in topologically incomplete networksPhysica A2017Xin et al.[Paper]

GCN-based Community Detection

Paper TitleVenueYearMethodMaterials
Complex exponential graph convolutional networksInf. Sci.2023CEGCN[Paper] [Code]
Community detection based on community perspective and graph convolutional networkExpert Syst. Appl.2023CPGC[Paper]
Heterogeneous question answering community detection based on graph neural networkInf. Sci.2023HCDBG[Paper]
Overlapping community detection on complex networks with graph convolutional networksComput. Commun.2023CDMG[Paper]
Deep MinCut: Learning node embeddings from detecting communitiesPattern Recognit.2022DMC[Paper]
End-to-end modularity-based community co-partition in bipartite networksCIKM2022BiCoN+GCN[Paper]
CLARE: A semi-supervised community detection algorithmKDD2022CLARE[Paper] [Code]
Efficient graph convolution for joint node representation learning and clusteringWSDM2022GCC[Paper] [Code]
Geometric graph representation learning via maximizing rate reductionWWW2022$G^2R$[Paper] [Code]
RepBin: Constraint-based graph representation learning for metagenomic binningAAAI2022RepBin[Paper] [Code]
SSSNET: Semi-supervised signed network clusteringSDM2022SSSNET[Paper] [Code]
Learning Guarantees for Graph Convolutional Networks on The Stochastic Block ModelICLR2022GCN-SBM[Paper]
When convolutional network meets temporal heterogeneous graphs: An effective community detection methodIEEE TKDE2021THGCN[Paper]
Multi-view contrastive graph clusteringNIPS2021MCGC[paper] [Code]
Graph debiased contrastive learning with joint representation clusteringIJCAI2021Zhao et al.[Paper]
Spectral embedding network for attributed graph clusteringNeural Netw.2021SENet[Paper]
Unsupervised learning for community detection in attributed networks based on graph convolutional networkNeurocomputing2021SGCN[Paper]
Adaptive graph encoder for attributed graph embeddingKDD2020AGE[Paper][Code]
CommDGI: Community detection oriented deep graph infomaxCIKM2020CommDGI[Paper]
Going deep: Graph convolutional ladder-shape networksAAAI2020GCLN[Paper]
Independence promoted graph disentangled networksAAAI2020IPGDN[Paper]
Supervised community detection with line graph neural networksICLR2019LGNN[Paper][Code]
Graph convolutional networks meet Markov random fields: Semi-supervised community detection in attribute networksAAAI2019MRFasGCN[Paper]
Overlapping community detection with graph neural networksDLG Workshop, KDD2019NOCD[Paper][Code]
Attributed graph clustering via adaptive graph convolutionIJCAI2019AGC[Paper][Code]
CayleyNets: Graph convolutional neural networks with complex rational spectral filtersIEEE TSP2019CayleyNets[Paper][Code]

Graph Attention Network-based Community Detection

Paper TitleVenueYearMethodMaterials
CSAT: Contrastive sampling-aggregating transformer for community detection in attribute-missing networksIEEE TCSS2023CSAT[Paper]
A graph-enhanced attention model for community detection in multiplex networksExpert Syst. Appl.2023GEAM[Paper][Code]
Hierarchical attention network for attributed community detection of joint representationNeural Comput. Appl.2022HiAN[Paper]
Detecting communities from heterogeneous graphs: A context path-based graph neural network modelCIKM2021<nobr> CP-GNN <nobr>[Paper][Code]
HDMI: High-order deep multiplex infomaxWWW2021HDMI[Paper][Code]
Self-supervised heterogeneous graph neural network with co-contrastive learningKDD2021HeCo[Paper][Code]
Unsupervised attributed multiplex network embeddingAAAI2020DMGI[Paper][Code]
MAGNN: Metapath aggregated graph neural network for heterogeneous graph embeddingWWW2020MAGNN[Paper] [Code]

Graph Adversarial Network-based Community Detection

Paper TitleVenueYearMethodMaterials
CANE: Community-aware network embedding via adversarial trainingKnowl. Inf. Syst.2021CANE[Paper]
Self-training enhanced: Network embedding and overlapping community detection with adversarial learningIEEE TNNLS2021ACNE <br> ACNE-ST <br>[Paper]
Adversarial Learning of Balanced Triangles for Accurate Community Detection on Signed NetworksICDM2021ABC[Paper]
SEAL: Learning heuristics for community detection with generative adversarial networksKDD2020SEAL[Paper][Code]
Multi-class imbalanced graph convolutional network learningIJCAI2020DR-GCN[Paper]
JANE: Jointly adversarial network embeddingIJCAI2020JANE[Paper]
ProGAN: Network embedding via

编辑推荐精选

AEE

AEE

AI Excel全自动制表工具

AEE 在线 AI 全自动 Excel 编辑器,提供智能录入、自动公式、数据整理、图表生成等功能,高效处理 Excel 任务,提升办公效率。支持自动高亮数据、批量计算、不规则数据录入,适用于企业、教育、金融等多场景。

UI-TARS-desktop

UI-TARS-desktop

基于 UI-TARS 视觉语言模型的桌面应用,可通过自然语言控制计算机进行多模态操作。

UI-TARS-desktop 是一款功能强大的桌面应用,基于 UI-TARS(视觉语言模型)构建。它具备自然语言控制、截图与视觉识别、精确的鼠标键盘控制等功能,支持跨平台使用(Windows/MacOS),能提供实时反馈和状态显示,且数据完全本地处理,保障隐私安全。该应用集成了多种大语言模型和搜索方式,还可进行文件系统操作。适用于需要智能交互和自动化任务的场景,如信息检索、文件管理等。其提供了详细的文档,包括快速启动、部署、贡献指南和 SDK 使用说明等,方便开发者使用和扩展。

Wan2.1

Wan2.1

开源且先进的大规模视频生成模型项目

Wan2.1 是一个开源且先进的大规模视频生成模型项目,支持文本到图像、文本到视频、图像到视频等多种生成任务。它具备丰富的配置选项,可调整分辨率、扩散步数等参数,还能对提示词进行增强。使用了多种先进技术和工具,在视频和图像生成领域具有广泛应用前景,适合研究人员和开发者使用。

爱图表

爱图表

全流程 AI 驱动的数据可视化工具,助力用户轻松创作高颜值图表

爱图表(aitubiao.com)就是AI图表,是由镝数科技推出的一款创新型智能数据可视化平台,专注于为用户提供便捷的图表生成、数据分析和报告撰写服务。爱图表是中国首个在图表场景接入DeepSeek的产品。通过接入前沿的DeepSeek系列AI模型,爱图表结合强大的数据处理能力与智能化功能,致力于帮助职场人士高效处理和表达数据,提升工作效率和报告质量。

Qwen2.5-VL

Qwen2.5-VL

一款强大的视觉语言模型,支持图像和视频输入

Qwen2.5-VL 是一款强大的视觉语言模型,支持图像和视频输入,可用于多种场景,如商品特点总结、图像文字识别等。项目提供了 OpenAI API 服务、Web UI 示例等部署方式,还包含了视觉处理工具,有助于开发者快速集成和使用,提升工作效率。

HunyuanVideo

HunyuanVideo

HunyuanVideo 是一个可基于文本生成高质量图像和视频的项目。

HunyuanVideo 是一个专注于文本到图像及视频生成的项目。它具备强大的视频生成能力,支持多种分辨率和视频长度选择,能根据用户输入的文本生成逼真的图像和视频。使用先进的技术架构和算法,可灵活调整生成参数,满足不同场景的需求,是文本生成图像视频领域的优质工具。

WebUI for Browser Use

WebUI for Browser Use

一个基于 Gradio 构建的 WebUI,支持与浏览器智能体进行便捷交互。

WebUI for Browser Use 是一个强大的项目,它集成了多种大型语言模型,支持自定义浏览器使用,具备持久化浏览器会话等功能。用户可以通过简洁友好的界面轻松控制浏览器智能体完成各类任务,无论是数据提取、网页导航还是表单填写等操作都能高效实现,有利于提高工作效率和获取信息的便捷性。该项目适合开发者、研究人员以及需要自动化浏览器操作的人群使用,在 SEO 优化方面,其关键词涵盖浏览器使用、WebUI、大型语言模型集成等,有助于提高网页在搜索引擎中的曝光度。

xiaozhi-esp32

xiaozhi-esp32

基于 ESP32 的小智 AI 开发项目,支持多种网络连接与协议,实现语音交互等功能。

xiaozhi-esp32 是一个极具创新性的基于 ESP32 的开发项目,专注于人工智能语音交互领域。项目涵盖了丰富的功能,如网络连接、OTA 升级、设备激活等,同时支持多种语言。无论是开发爱好者还是专业开发者,都能借助该项目快速搭建起高效的 AI 语音交互系统,为智能设备开发提供强大助力。

olmocr

olmocr

一个用于 OCR 的项目,支持多种模型和服务器进行 PDF 到 Markdown 的转换,并提供测试和报告功能。

olmocr 是一个专注于光学字符识别(OCR)的 Python 项目,由 Allen Institute for Artificial Intelligence 开发。它支持多种模型和服务器,如 vllm、sglang、OpenAI 等,可将 PDF 文件的页面转换为 Markdown 格式。项目还提供了测试框架和 HTML 报告生成功能,方便用户对 OCR 结果进行评估和分析。适用于科研、文档处理等领域,有助于提高工作效率和准确性。

飞书多维表格

飞书多维表格

飞书多维表格 ×DeepSeek R1 满血版

飞书多维表格联合 DeepSeek R1 模型,提供 AI 自动化解决方案,支持批量写作、数据分析、跨模态处理等功能,适用于电商、短视频、影视创作等场景,提升企业生产力与创作效率。关键词:飞书多维表格、DeepSeek R1、AI 自动化、批量处理、企业协同工具。

下拉加载更多