[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-tsinghua-fib-lab--GNN-Recommender-Systems":3,"tool-tsinghua-fib-lab--GNN-Recommender-Systems":65},[4,23,32,40,49,57],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":22},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。",84991,2,"2026-04-05T10:45:23",[13,14,15,16,17,18,19,20,21],"图像","数据工具","视频","插件","Agent","其他","语言模型","开发框架","音频","ready",{"id":24,"name":25,"github_repo":26,"description_zh":27,"stars":28,"difficulty_score":29,"last_commit_at":30,"category_tags":31,"status":22},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。",77062,3,"2026-04-04T04:44:48",[17,13,20,19,18],{"id":33,"name":34,"github_repo":35,"description_zh":36,"stars":37,"difficulty_score":29,"last_commit_at":38,"category_tags":39,"status":22},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",74939,"2026-04-05T23:16:38",[19,13,20,18],{"id":41,"name":42,"github_repo":43,"description_zh":44,"stars":45,"difficulty_score":46,"last_commit_at":47,"category_tags":48,"status":22},3215,"awesome-machine-learning","josephmisiti\u002Fawesome-machine-learning","awesome-machine-learning 是一份精心整理的机器学习资源清单，汇集了全球优秀的机器学习框架、库和软件工具。面对机器学习领域技术迭代快、资源分散且难以甄选的痛点，这份清单按编程语言（如 Python、C++、Go 等）和应用场景（如计算机视觉、自然语言处理、深度学习等）进行了系统化分类，帮助使用者快速定位高质量项目。\n\n它特别适合开发者、数据科学家及研究人员使用。无论是初学者寻找入门库，还是资深工程师对比不同语言的技术选型，都能从中获得极具价值的参考。此外，清单还延伸提供了免费书籍、在线课程、行业会议、技术博客及线下聚会等丰富资源，构建了从学习到实践的全链路支持体系。\n\n其独特亮点在于严格的维护标准：明确标记已停止维护或长期未更新的项目，确保推荐内容的时效性与可靠性。作为机器学习领域的“导航图”，awesome-machine-learning 以开源协作的方式持续更新，旨在降低技术探索门槛，让每一位从业者都能高效地站在巨人的肩膀上创新。",72149,1,"2026-04-03T21:50:24",[20,18],{"id":50,"name":51,"github_repo":52,"description_zh":53,"stars":54,"difficulty_score":46,"last_commit_at":55,"category_tags":56,"status":22},2234,"scikit-learn","scikit-learn\u002Fscikit-learn","scikit-learn 是一个基于 Python 构建的开源机器学习库，依托于 SciPy、NumPy 等科学计算生态，旨在让机器学习变得简单高效。它提供了一套统一且简洁的接口，涵盖了从数据预处理、特征工程到模型训练、评估及选择的全流程工具，内置了包括线性回归、支持向量机、随机森林、聚类等在内的丰富经典算法。\n\n对于希望快速验证想法或构建原型的数据科学家、研究人员以及 Python 开发者而言，scikit-learn 是不可或缺的基础设施。它有效解决了机器学习入门门槛高、算法实现复杂以及不同模型间调用方式不统一的痛点，让用户无需重复造轮子，只需几行代码即可调用成熟的算法解决分类、回归、聚类等实际问题。\n\n其核心技术亮点在于高度一致的 API 设计风格，所有估算器（Estimator）均遵循相同的调用逻辑，极大地降低了学习成本并提升了代码的可读性与可维护性。此外，它还提供了强大的模型选择与评估工具，如交叉验证和网格搜索，帮助用户系统地优化模型性能。作为一个由全球志愿者共同维护的成熟项目，scikit-learn 以其稳定性、详尽的文档和活跃的社区支持，成为连接理论学习与工业级应用的最",65628,"2026-04-05T10:10:46",[20,18,14],{"id":58,"name":59,"github_repo":60,"description_zh":61,"stars":62,"difficulty_score":10,"last_commit_at":63,"category_tags":64,"status":22},3364,"keras","keras-team\u002Fkeras","Keras 是一个专为人类设计的深度学习框架，旨在让构建和训练神经网络变得简单直观。它解决了开发者在不同深度学习后端之间切换困难、模型开发效率低以及难以兼顾调试便捷性与运行性能的痛点。\n\n无论是刚入门的学生、专注算法的研究人员，还是需要快速落地产品的工程师，都能通过 Keras 轻松上手。它支持计算机视觉、自然语言处理、音频分析及时间序列预测等多种任务。\n\nKeras 3 的核心亮点在于其独特的“多后端”架构。用户只需编写一套代码，即可灵活选择 TensorFlow、JAX、PyTorch 或 OpenVINO 作为底层运行引擎。这一特性不仅保留了 Keras 一贯的高层易用性，还允许开发者根据需求自由选择：利用 JAX 或 PyTorch 的即时执行模式进行高效调试，或切换至速度最快的后端以获得最高 350% 的性能提升。此外，Keras 具备强大的扩展能力，能无缝从本地笔记本电脑扩展至大规模 GPU 或 TPU 集群，是连接原型开发与生产部署的理想桥梁。",63927,"2026-04-04T15:24:37",[20,14,18],{"id":66,"github_repo":67,"name":68,"description_en":69,"description_zh":70,"ai_summary_zh":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":80,"owner_location":80,"owner_email":81,"owner_twitter":80,"owner_website":82,"owner_url":83,"languages":80,"stars":84,"forks":85,"last_commit_at":86,"license":80,"difficulty_score":87,"env_os":79,"env_gpu":88,"env_ram":88,"env_deps":89,"category_tags":92,"github_topics":93,"view_count":10,"oss_zip_url":80,"oss_zip_packed_at":80,"status":22,"created_at":104,"updated_at":105,"faqs":106,"releases":107},3672,"tsinghua-fib-lab\u002FGNN-Recommender-Systems","GNN-Recommender-Systems","An index of recommendation algorithms that are based on Graph Neural Networks. (TORS)","GNN-Recommender-Systems 是一个专注于图神经网络（GNN）在推荐系统领域应用的开源算法索引库。它旨在解决研究人员和开发者在面对海量 GNN 推荐论文时，难以快速梳理技术脉络、查找对应代码及对比不同场景适用性的痛点。\n\n该资源不仅汇总了从匹配、排序到重排序等推荐全阶段的经典算法（如 LightGCN、Pin-Sage 等），还细致地按社交推荐、序列推荐、跨域推荐等不同应用场景，以及多样性、公平性、可解释性等优化目标进行了分类整理。其独特的技术亮点在于依托一篇被 ACM TORS 接收的权威综述论文构建，确保了收录内容的学术前沿性与系统性，并为多数算法提供了直接的代码链接，极大地降低了复现门槛。\n\n无论是希望追踪最新学术动态的高校研究人员，还是寻求高效解决方案的算法工程师，都能从中获得极大帮助。对于想要深入理解如何利用图结构挖掘用户与物品复杂关系的技术从业者而言，GNN-Recommender-Systems 是一份不可多得的实战指南与知识地图。","# GNN based Recommender Systems\nAn index of recommendation algorithms that are based on Graph Neural Networks.\n\nOur survey **A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions** is accepted by ACM Transactions on Recommender Systems.\nA preprint is available on arxiv: [link](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.12843v2.pdf)\n\nPlease cite our survey paper if this index is helpful.\n```\n@article{gao2022survey,\n  title={A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions},\n  author={Gao, Chen and Zheng, Yu and Li, Nian and Li, Yinfeng and Qin, Yingrong and Piao, Jinghua and Quan, Yuhan and Chang, Jianxin and Jin, Depeng and He, Xiangnan and Li, Yong},\n  journal={ACM Transactions on Recommender Systems (TORS)},\n  year={2022}\n}\n```\n```\nGao, C., Zheng, Y., Li, N., Li, Y., Qin, Y., Piao, J., Quan, Y., Chang, J., Jin, D., He, X., & Li, Y. (2022). A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions. ACM Transactions on Recommender Systems (TORS).\n```\n\n# Table of Contents\n\n- [GNN in different recommendation stages](#Recommendation-Stages)\n   - [Matching](#Matching)\n   - [Ranking](#Ranking)\n   - [Re-ranking](#Re-ranking)\n- [GNN in different recommendation scenarios](#Recommendation-Scenarios)\n   - [Social Recommendation](#Social-Recommendation)\n   - [Sequential Recommendation](#Sequential-Recommendation)\n   - [Session Recommendation](#Session-Recommendation)\n   - [Bundle Recommendation](#Bundle-Recommendation)\n   - [Cross Domain Recommendation](#Cross-Domain-Recommendation)\n- [GNN for different recommendation objectives](#Recommendation-Objectives)\n   - [Multi-behavior Recommendation](#Multi-behavior-Recommendation)\n   - [Diversity](#Diversity)\n   - [Explainability](#Explainability)\n   - [Fairness](#Fairness)\n## Recommendation Stages\n### Matching\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| GCMC | [Berg, R. V. D., Kipf, T. N., & Welling, M. (2017). Graph convolutional matrix completion. _arXiv preprint arXiv:1706.02263_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.02263.pdf) | arxiv | 2017 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fgraph-convolutional-matrix-completion) |\n| Pin-Sage | [Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., & Leskovec, J. (2018, July). Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 974-983).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1806.01973) | KDD | 2018 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fgraph-convolutional-neural-networks-for-web) |\n| NGCF | [Wang, X., He, X., Wang, M., Feng, F., & Chua, T. S. (2019, July). Neural graph collaborative filtering. In _Proceedings of the 42nd international ACM SIGIR conference on Research and development in Information Retrieval_ (pp. 165-174).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.08108.pdf) | SIGIR | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fneural-graph-collaborative-filtering) |\n| LightGCN | [He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., & Wang, M. (2020, July). Lightgcn: Simplifying and powering graph convolution network for recommendation. In _Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval_ (pp. 639-648).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.02126.pdf) | SIGIR | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Flightgcn-simplifying-and-powering-graph) |\n| NIA-GCN | [Sun, J., Zhang, Y., Guo, W., Guo, H., Tang, R., He, X., ... & Coates, M. (2020, July). Neighbor interaction aware graph convolution networks for recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1289-1298).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3397271.3401123) | SIGIR | 2020 | NA |\n| DGCF | [Wang, X., Jin, H., Zhang, A., He, X., Xu, T., & Chua, T. S. (2020, July). Disentangled graph collaborative filtering. In _Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 1001-1010).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.01764) | SIGIR | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fdisentangled-graph-collaborative-filtering) |\n| IMP-GCN | [Liu, F., Cheng, Z., Zhu, L., Gao, Z., & Nie, L. (2021, April). Interest-aware message-passing gcn for recommendation. In Proceedings of the Web Conference 2021 (pp. 1296-1305).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.10044.pdf) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fliufancs\u002FIMP_GCN) |\n| SGL | [Wu, J., Wang, X., Feng, F., He, X., Chen, L., Lian, J., & Xie, X. (2021, July). Self-supervised graph learning for recommendation. In _Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 726-735).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.10783) | SIGIR | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fwujcan\u002FSGL) |\n| LT-OCF | [Choi, J., Jeon, J., & Park, N. (2021). LT-OCF: Learnable-Time ODE-based Collaborative Filtering. In _Proceedings of the 30th ACM International Conference on Information and Knowledge Management_ (pp. 251-260).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3459637.3482449) | CIKM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FLT-OCF) |\n| HMLET | [Kong, T., Kim, T., Jeon, J., Choi, J., Lee, Y-C.,Park, N., & Kim, S-W. (2022). Linear, or Non-Linear, That is the Question! In _Proceedings of the 15th ACM International Web Search and Data Mining Conference_ (pp. 517-525).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498501) | WSDM | 2022 | [Python](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FHMLET) | \n| HS-GCN | [Liu, H., Wei, Y., Yin, J., & Nie, L. (2022). HS-GCN: Hamming Spatial Graph Convolutional Networks for Recommendation. IEEE Transactions on Knowledge and Data Engineering.](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9732648) | TKDE | 2022 | [Python](https:\u002F\u002Fgithub.com\u002Fhanliu95\u002FHS-GCN) |\n| LGCN | [Yu, W., Zhang, Z., & Qin, Z. (2022). Low-pass Graph Convolutional Network for Recommendation.](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-3643.WenhuiY.pdf) | AAAI | 2022 | [Python](https:\u002F\u002Fgithub.com\u002FWenhui-Yu\u002FLCFN) |\n\n### Ranking\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| Fi-GNN | [Li, Z., Cui, Z., Wu, S., Zhang, X., & Wang, L. (2019, November). Fi-gnn: Modeling feature interactions via graph neural networks for ctr prediction. In _Proceedings of the 28th ACM International Conference on Information and Knowledge Management_ (pp. 539-548).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.05552.pdf) | CIKM | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Ffi-gnn-modeling-feature-interactions-via) |\n| PUP | [Zheng, Y., Gao, C., He, X., Li, Y., & Jin, D. (2020, April). Price-aware recommendation with graph convolutional networks. In _2020 IEEE 36th International Conference on Data Engineering (ICDE)_ (pp. 133-144). IEEE.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2003.03975.pdf) | ICDE | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FDavyMorgan\u002FICDE20-PUP) |\n|A2-GCN | [Liu, F., Cheng, Z., Zhu, L., Liu, C., & Nie, L. (2020). A2-GCN: An attribute-aware attentive GCN model for recommendation. IEEE Transactions on Knowledge and Data Engineering.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2003.09086.pdf) | TKDE | 2020 | NA |\n| L\u003Csub>0\u003C\u002Fsub>-SIGN | [Su, Y., Zhang, R., Erfani, S., & Xu, Z. (2021, May). Detecting Beneficial Feature Interactions for Recommender Systems. In _Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI)_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.00404.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fruizhang-ai\u002FSIGN-Detecting-Beneficial-Feature-Interactions-for-Recommender-Systems) |\n| DG-ENN | [Guo, W., Su, R., Tan, R., Guo, H., Zhang, Y., Liu, Z., ... & He, X. (2021). Dual Graph enhanced Embedding Neural Network for CTRPrediction. _arXiv preprint arXiv:2106.00314_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.00314.pdf) | KDD | 2021 | NA |\n| SHCF | [Li, C., Hu, L., Shi, C., Song, G., & Lu, Y. (2021). Sequence-aware Heterogeneous Graph Neural Collaborative Filtering. In _Proceedings of the 2021 SIAM International Conference on Data Mining (SDM)_ (pp. 64-72). Society for Industrial and Applied Mathematics.](http:\u002F\u002Fwww.shichuan.org\u002Fdoc\u002F98.pdf) | SDM | 2021 | [Python](http:\u002F\u002Fwww.shichuan.org\u002Fdataset\u002FSHCF.zip) |\n| GCM | [Wu, J., He, X., Wang, X., Wang, Q., Chen, W., Lian, J., & Xie, X. (2020). Graph Convolution Machine for Context-aware Recommender System. _arXiv preprint arXiv:2001.11402_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.11402.pdf) | Frontiers of Computer Science | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fwujcan\u002FGCM) |\n| TGIN | [Jiang, W., Jiao, Y., Wang, Q., Liang, C., Guo, L., Zhang, Y., ... & Zhu, Y. (2022, February). Triangle Graph Interest Network for Click-through Rate Prediction. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (pp. 401-409).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.02698.pdf) | WSDM | 2022 | [Python](https:\u002F\u002Fgithub.com\u002Falibaba\u002Ftgin) |\n\n### Re-ranking\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| IRGPR | [Liu, W., Liu, Q., Tang, R., Chen, J., He, X., & Heng, P. A. (2020, October). Personalized Re-ranking with Item Relationships for E-commerce. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 925-934).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412332) | CIKM | 2020 | NA |\n\n## Recommendation Scenarios\n### Social Recommendation\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| DiffNet | [Wu, L., Sun, P., Fu, Y., Hong, R., Wang, X., & Wang, M. (2019, July). A neural influence diffusion model for social recommendation. In _Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval_ (pp. 235-244).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.10322) | SIGIR | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fa-neural-influence-diffusion-model-for-social) |\n| GraphRec | [Fan, W., Ma, Y., Li, Q., He, Y., Zhao, E., Tang, J., & Yin, D. (2019, May). Graph neural networks for social recommendation. In _The World Wide Web Conference_ (pp. 417-426).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.07243) | WWW | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fgraph-neural-networks-for-social) |\n| DANSER | [Wu, Q., Zhang, H., Gao, X., He, P., Weng, P., Gao, H., & Chen, G. (2019, May). Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems. In _The World Wide Web Conference_ (pp. 2091-2102).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.10433) | WWW | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fqitianwu\u002FDANSER-WWW-19) |\n| DGRec | [Song, W., Xiao, Z., Wang, Y., Charlin, L., Zhang, M., & Tang, J. (2019, January). Session-based social recommendation via dynamic graph attention networks. In _Proceedings of the Twelfth ACM international conference on web search and data mining_ (pp. 555-563).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.09362) | WSDM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FRecommenderSystems) |\n| HGP | [Kim, K. M., Kwak, D., Kwak, H., Park, Y. J., Sim, S., Cho, J. H., ... & Ha, J. W. (2019). Tripartite heterogeneous graph propagation for large-scale social recommendation. _arXiv preprint arXiv:1908.02569_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.02569) | RecSys | 2019 | NA |\n| DiffNet++ | [Wu, L., Li, J., Sun, P., Hong, R., Ge, Y., & Wang, M. (2020). Diffnet++: A neural influence and interest diffusion network for social recommendation. IEEE Transactions on Knowledge and Data Engineering.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.00844.pdf) | TKDE | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fdiffnet-a-neural-influence-and-interest)\n| MHCN | [Yu, J., Yin, H., Li, J., Wang, Q., Hung, N. Q. V., & Zhang, X. (2021, April). Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation. In _Proceedings of the Web Conference 2021_ (pp. 413-424).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2101.06448) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FCoder-Yu\u002FQRec) |\n| SEPT | [Yu, J., Yin, H., Gao, M., Xia, X., Zhang, X., & Hung, N. Q. V. (2021). Socially-Aware Self-Supervised Tri-Training for Recommendation. _arXiv preprint arXiv:2106.03569_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.03569) | KDD | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FCoder-Yu\u002FQRec) |\n| GBGCN | [Zhang, J., Gao, C., Jin, D., & Li, Y. (2021, April). Group-Buying Recommendation for Social E-Commerce. In _2021 IEEE 37th International Conference on Data Engineering (ICDE)_ (pp. 1536-1547). IEEE.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.06848) | ICDE | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FSweetnow\u002Fgroup-buying-recommendation) |\n| KCGN | [Huang, C., Xu, H., Xu, Y., Dai, P., Xia, L., Lu, M., ... & Ye, Y. (2021, January). Knowledge-aware coupled graph neural network for social recommendation. In _AAAI Conference on Artificial Intelligence (AAAI)_.](https:\u002F\u002Fwww.aaai.org\u002FAAAI21Papers\u002FAAAI-9069.HuangC.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fxhcdream\u002FKCGN) |\n| DiffNetLG | [Song, C., Wang, B., Jiang, Q., Zhang, Y., He, R., & Hou, Y. (2021, July). Social Recommendation with Implicit Social Influence. In _Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 1788-1792).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3404835.3463043) | SIGIR | 2021 | NA |\n| RecoGCN | [Xu, F., Lian, J., Han, Z., Li, Y., Xu, Y., & Xie, X. (2019, November). Relation-aware graph convolutional networks for agent-initiated social e-commerce recommendation. In _Proceedings of the 28th ACM international conference on information and knowledge management_ (pp. 529-538).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3357384.3357924) | CIKM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fxfl15\u002FRecoGCN) |\n| GAT-NSR | [Mu, N., Zha, D., He, Y., & Tang, Z. (2019, November). Graph attention networks for neural social recommendation. In _2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)_ (pp. 1320-1327). IEEE.](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8995280) | ICTAI | 2019 | NA |\n| SR-HGNN | [Xu, H., Huang, C., Xu, Y., Xia, L., Xing, H., & Yin, D. (2020, November). Global context enhanced social recommendation with hierarchical graph neural networks. In _2020 IEEE International Conference on Data Mining (ICDM)_ (pp. 701-710). IEEE.](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338365) | ICDM | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fxhcdream\u002FSR-HGNN) |\n| TGRec | [Bai, T., Zhang, Y., Wu, B., & Nie, J. Y. (2020, December). Temporal Graph Neural Networks for Social Recommendation. In _2020 IEEE International Conference on Big Data (Big Data)_ (pp. 898-903). IEEE.](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9378444) | ICBD | 2020 | NA |\n| ESRF | [Yu, J., Yin, H., Li, J., Gao, M., Huang, Z., & Cui, L. (2020). Enhance social recommendation with adversarial graph convolutional networks. _IEEE Transactions on Knowledge and Data Engineering_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.02340) | TKDE | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FCoder-Yu\u002FQRec) |\n| HOSR | [Liu, Y., Liang, C., He, X., Peng, J., Zheng, Z., & Tang, J. (2020). Modelling high-order social relations for item recommendation. _IEEE Transactions on Knowledge and Data Engineering_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2003.10149) | TKDE | 2020 | NA |\n| GNN-SoR | [Guo, Z., & Wang, H. (2020). A deep graph neural network-based mechanism for social recommendations. _IEEE Transactions on Industrial Informatics_, _17_(4), 2776-2783.](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9063418) | TII | 2020 | NA |\n| ASR | [Luo, D., Bian, Y., Zhang, X., & Huan, J. (2020). Attentive Social Recommendation: Towards User And Item Diversities. _arXiv preprint arXiv:2011.04797_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.04797) | arxiv | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fflyingdoog\u002FASR) |\n\n### Sequential Recommendation\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| ISSR | [Liu, F., Liu, W., Li, X., & Ye, Y. (2020). Inter-sequence Enhanced Framework for Personalized Sequential Recommendation. _arXiv preprint arXiv:2004.12118_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12118) | AAAI | 2020 | NA |\n| MA-GNN | [Ma, C., Ma, L., Zhang, Y., Sun, J., Liu, X., & Coates, M. (2020, April). Memory augmented graph neural networks for sequential recommendation. In _Proceedings of the AAAI Conference on Artificial Intelligence_ (Vol. 34, No. 04, pp. 5045-5052).](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fdownload\u002F5945\u002F5801) | AAAI | 2020 | NA |\n| STP-UDGAT | [Lim, N., Hooi, B., Ng, S. K., Wang, X., Goh, Y. L., Weng, R., & Varadarajan, J. (2020, October). STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendation. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 845-854).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.07024) | CIKM | 2020 | NA |\n| GPR | [Chang, B., Jang, G., Kim, S., & Kang, J. (2020, October). Learning graph-based geographical latent representation for point-of-interest recommendation. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 135-144).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3411905) | CIKM | 2020 | NA |\n| GES-SASRec | [Zhu, T., Sun, L., & Chen, G. (2021). Graph-based Embedding Smoothing for Sequential Recommendation. _IEEE Transactions on Knowledge and Data Engineering_.](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9405450\u002F) | TKDE | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fzhuty16\u002FGES) |\n| RetaGNN | [Hsu, C., & Li, C. T. (2021, April). RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation. In _Proceedings of the Web Conference 2021_ (pp. 2968-2979).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2101.12457) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fretagnn\u002FRetaGNN) |\n| TGSRec | [Fan, Z., Liu, Z., Zhang, J., Xiong, Y., Zheng, L., & Yu, P. S. (2021). Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer. _arXiv preprint arXiv:2108.06625_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2108.06625) | CIKM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FDyGRec\u002FTGSRec) |\n| SGRec | [Li, Y., Chen, T., Yin, H., & Huang, Z. (2021). Discovering Collaborative Signals for Next POI Recommendation with Iterative Seq2Graph Augmentation. _arXiv preprint arXiv:2106.15814_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.15814) | IJCAI | 2021 | NA |\n| SURGE | [Chang, J., Gao, C., Zheng, Y., Hui, Y., Niu, Y., Song, Y., ... & Li, Y. (2021, July). Sequential Recommendation with Graph Neural Networks. In _Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 378-387).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.14226) | SIGIR | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FSIGIR21-SURGE) |\n| GME | [Xie, M., Yin, H., Xu, F., Wang, H., & Zhou, X. (2016, November). Graph-based metric embedding for next poi recommendation. In _International Conference on Web Information Systems Engineering_ (pp. 207-222). Springer, Cham.](http:\u002F\u002Fnet.pku.edu.cn\u002Fdaim\u002Fhongzhi.yin\u002Fpapers\u002FWISE-2016.pdf) | WISE | 2016 | NA |\n| Wang _et al._ | [Wang, B., & Cai, W. (2020). Knowledge-enhanced graph neural networks for sequential recommendation. _Information_, _11_(8), 388.](https:\u002F\u002Fwww.mdpi.com\u002F2078-2489\u002F11\u002F8\u002F388\u002Fpdf) | Information | 2020 | NA |\n| DGSR | [Zhang, M., Wu, S., Yu, X., & Wang, L. (2021). Dynamic Graph Neural Networks for Sequential Recommendation. _arXiv preprint arXiv:2104.07368_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2104.07368) | arxiv | 2021 | NA |\n\n### Session Recommendation\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| SR-GNN | [Wu, S., Tang, Y., Zhu, Y., Wang, L., Xie, X., & Tan, T. (2019, July). Session-based recommendation with graph neural networks. In _Proceedings of the AAAI Conference on Artificial Intelligence_ (Vol. 33, No. 01, pp. 346-353).](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3804\u002F3682) | AAAI | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fsession-based-recommendation-with-graph) |\n| GC-SAN | [Xu, C., Zhao, P., Liu, Y., Sheng, V. S., Xu, J., Zhuang, F., ... & Zhou, X. (2019, August). Graph Contextualized Self-Attention Network for Session-based Recommendation. In _IJCAI_ (Vol. 19, pp. 3940-3946).](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0547.pdf) | IJCAI | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FRUCAIBox\u002FRecBole\u002Fblob\u002Fmaster\u002Frecbole\u002Fmodel\u002Fsequential_recommender\u002Fgcsan.py) |\n| TA-GNN | [Yu, F., Zhu, Y., Liu, Q., Wu, S., Wang, L., & Tan, T. (2020, July). TAGNN: Target attentive graph neural networks for session-based recommendation. In _Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 1921-1924).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.02844) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FTAGNN) |\n| MGNN-SPred | [Wang, W., Zhang, W., Liu, S., Liu, Q., Zhang, B., Lin, L., & Zha, H. (2020, April). Beyond clicks: Modeling multi-relational item graph for session-based target behavior prediction. In _Proceedings of The Web Conference 2020_ (pp. 3056-3062).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.07993) | WWW | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FAutumn945\u002FMGNN-SPred) |\n| LESSR | [Chen, T., & Wong, R. C. W. (2020, August). Handling information loss of graph neural networks for session-based recommendation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 1172-1180).](http:\u002F\u002Fhome.cse.ust.hk\u002F~raywong\u002Fpaper\u002Fkdd20-informationLoss-GNN.pdf) | KDD | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Ftwchen\u002Flessr) |\n| MKM-SR | [Meng, W., Yang, D., & Xiao, Y. (2020, July). Incorporating user micro-behaviors and item knowledge into multi-task learning for session-based recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1091-1100).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.06922) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fciecus\u002FMKM-SR) |\n| GAG | [Qiu, R., Yin, H., Huang, Z., & Chen, T. (2020, July). Gag: Global attributed graph neural network for streaming session-based recommendation. In _Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 669-678).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.02747) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FRuihongQiu\u002FGAG) |\n| GCE-GNN | [Wang, Z., Wei, W., Cong, G., Li, X. L., Mao, X. L., & Qiu, M. (2020, July). Global context enhanced graph neural networks for session-based recommendation. In _Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 169-178).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.05081) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FCCIIPLab\u002FGCE-GNN) |\n| SGNN-HN | [Pan, Z., Cai, F., Chen, W., Chen, H., & de Rijke, M. (2020, October). Star graph neural networks for session-based recommendation. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 1195-1204).](https:\u002F\u002Firlab.science.uva.nl\u002Fwp-content\u002Fpapercite-data\u002Fpdf\u002Fpan-2020-star.pdf) | CIKM | 2020 | NA |\n| DHCN | [Xia, X., Yin, H., Yu, J., Wang, Q., Cui, L., & Zhang, X. (2020). Self-supervised hypergraph convolutional networks for session-based recommendation. _arXiv preprint arXiv:2012.06852_.](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16578) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fxiaxin1998\u002FDHCN) |\n| SHARE | [Wang, J., Ding, K., Zhu, Z., & Caverlee, J. (2021). Session-based Recommendation with Hypergraph Attention Networks. In _Proceedings of the 2021 SIAM International Conference on Data Mining (SDM)_ (pp. 82-90). Society for Industrial and Applied Mathematics.](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fpdf\u002F10.1137\u002F1.9781611976700.10) | SDM | 2021 | NA |\n| SERec | [Chen, T., & Wong, R. C. W. (2021, March). An Efficient and Effective Framework for Session-based Social Recommendation. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining (pp. 400-408).](http:\u002F\u002Fwww.cse.ust.hk\u002F~raywong\u002Fpaper\u002Fwsdm21-SEFrame.pdf) | WSDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ftwchen\u002FSEFrame) |\n| COTREC | [Xia, X., Yin, H., Yu, J., Shao, Y., & Cui, L. (2021). Self-Supervised Graph Co-Training for Session-based Recommendation. arXiv preprint arXiv:2108.10560.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2108.10560) | CIKM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fxiaxin1998\u002FCOTREC) |\n| DAT-MDI | [Chen, C., Guo, J., & Song, B. (2021, July). Dual Attention Transfer in Session-based Recommendation with Multi-dimensional Integration. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 869-878).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3404835.3462866) | SIGIR | 2021 | NA |\n| TASRec | [Zhou, H., Tan, Q., Huang, X., Zhou, K., & Wang, X. (2021). Temporal Augmented Graph Neural Networks for Session-Based Recommendations.](https:\u002F\u002Fwww4.comp.polyu.edu.hk\u002F~xiaohuang\u002Fdocs\u002FHuachi_sigir2021.pdf) | SIGIR | 2021 | NA |\n| G\u003Csup>3\u003C\u002Fsup>SR | [Deng, Z. H., Wang, C. D., Huang, L., Lai, J. H., & Philip, S. Y. (2022). G^ 3SR: Global Graph Guided Session-Based Recommendation. IEEE Transactions on Neural Networks and Learning Systems.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2203.06467.pdf) | TNNLS | 2022 | NA |\n| HG-GNN | [Pang, Y., Wu, L., Shen, Q., Zhang, Y., Wei, Z., Xu, F., ... & Pei, J. (2022, February). Heterogeneous global graph neural networks for personalized session-based recommendation. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (pp. 775-783).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2107.03813.pdf) | WSDM | 2022 | [Python](https:\u002F\u002Fgithub.com\u002F0215Arthur\u002FHG-GNN) |\n| CGL | [Pan, Z., Cai, F., Chen, W., Chen, C., & Chen, H. (2022). Collaborative Graph Learning for Session-based Recommendation. ACM Transactions on Information Systems (TOIS), 40(4), 1-26.](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3490479) | TOIS | 2022 | NA |\n| CAGE | [Sheu, H. S., & Li, S. (2020, September). Context-aware graph embedding for session-based news recommendation. In Fourteenth ACM conference on recommender systems (pp. 657-662).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3383313.3418477) | RecSys | 2020 | NA |\n| A-PGNN | [Zhang, M., Wu, S., Gao, M., Jiang, X., Xu, K., & Wang, L. (2020). Personalized graph neural networks with attention mechanism for session-aware recommendation. IEEE Transactions on Knowledge and Data Engineering.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.08887) | TKDE | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fpersonalizing-graph-neural-networks-with) |\n| DGTN | [Zheng, Y., Liu, S., Li, Z., & Wu, S. (2020, November). DGTN: Dual-channel Graph Transition Network for Session-based Recommendation. In _2020 International Conference on Data Mining Workshops (ICDMW)_ (pp. 236-242). IEEE.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.10002) | ICDMW | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fkunwuz\u002FDGTN) |\n| FGNN | [Qiu, R., Li, J., Huang, Z., & Yin, H. (2019, November). Rethinking the item order in session-based recommendation with graph neural networks. In _Proceedings of the 28th ACM International Conference on Information and Knowledge Management_ (pp. 579-588).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.11942) | CIKM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FRuihongQiu\u002FFGNN) |\n\n### Bundle Recommendation\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| BGCN | [Chang, J., Gao, C., He, X., Jin, D., & Li, Y. (2020, July). Bundle recommendation with graph convolutional networks. In _Proceedings of the 43rd international ACM SIGIR conference on Research and development in Information Retrieval_ (pp. 1673-1676).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.03475) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fcjx0525\u002FBGCN) |\n| HFGN | [Li, X., Wang, X., He, X., Chen, L., Xiao, J., & Chua, T. S. (2020, July). Hierarchical fashion graph network for personalized outfit recommendation. In _Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 159-168).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.12566) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fxcppy\u002Fhierarchical_fashion_graph_network) |\n| BundleNet | [Deng, Q., Wang, K., Zhao, M., Zou, Z., Wu, R., Tao, J., ... & Chen, L. (2020, October). Personalized Bundle Recommendation in Online Games. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 2381-2388).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2104.05307) | CIKM | 2020 | NA |\n| DPR | [Zheng, Z., Wang, C., Xu, T., Shen, D., Qin, P., Huai, B., ... & Chen, E. (2021, April). Drug Package Recommendation via Interaction-aware Graph Induction. In _Proceedings of the Web Conference 2021_ (pp. 1284-1295).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.03577) | WWW | 2021 | NA |\n| DPG | [Zheng, Z., Wang, C., Xu, T., Shen, D., Qin, P., Zhao, X., ... & Chen, E. (2022). Interaction-aware Drug Package Recommendation via Policy Gradient. ACM Transactions on Information Systems (TOIS).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3511020) | TOIS | 2022 | NA |\n| MIDGN | [Zhao, S., Wei, W., Zou, D., & Mao, X. (2022). Multi-view intent disentangle graph networks for bundle recommendation. arXiv preprint arXiv:2202.11425.](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F20359) | AAAI | 2022 | [Python](https:\u002F\u002Fgithub.com\u002FSnnzhao\u002FMIDGN) |\n\n### Cross Domain Recommendation\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| PPGN | [Zhao, C., Li, C., & Fu, C. (2019, November). Cross-domain recommendation via preference propagation graphnet. In _Proceedings of the 28th ACM International Conference on Information and Knowledge Management_ (pp. 2165-2168).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3358166) | CIKM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FWHUIR\u002FPPGN) |\n| BiTGCF | [Liu, M., Li, J., Li, G., & Pan, P. (2020, October). Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 885-894).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412012) | CIKM | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fsunshinelium\u002FBi-TGCF) |\n| DAN | [Wang, B., Zhang, C., Zhang, H., Lyu, X., & Tang, Z. (2020, October). Dual Autoencoder Network with Swap Reconstruction for Cold-Start Recommendation. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 2249-2252).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412069) | CIKM | 2020 | NA |\n| HeroGRAPH | [Cui, Q., Wei, T., Zhang, Y., & Zhang, Q. (2020). HeroGRAPH: A Heterogeneous Graph Framework for Multi-Target Cross-Domain Recommendation. In _ORSUM@ RecSys_.](http:\u002F\u002Fceur-ws.org\u002FVol-2715\u002Fpaper6.pdf) | RecSys | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fcuiqiang1990\u002FHeroGRAPH) |\n| DAGCN | [Guo, L., Tang, L., Chen, T., Zhu, L., Nguyen, Q. V. H., & Yin, H. (2021). DA-GCN: A Domain-aware Attentive Graph Convolution Network for Shared-account Cross-domain Sequential Recommendation. _arXiv preprint arXiv:2105.03300_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2105.03300) | IJCAI | 2021 | NA |\n\n## Recommendation Objectives\n### Multi-behavior Recommendation\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| MBGCN | [Jin, B., Gao, C., He, X., Jin, D., & Li, Y. (2020, July). Multi-behavior recommendation with graph convolutional networks. In _Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 659-668).](http:\u002F\u002Fstaff.ustc.edu.cn\u002F~hexn\u002Fpapers\u002Fsigir20-MBGCN.pdf) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FMBGCN) |\n| MGNN-SPred | [Wang, W., Zhang, W., Liu, S., Liu, Q., Zhang, B., Lin, L., & Zha, H. (2020, April). Beyond clicks: Modeling multi-relational item graph for session-based target behavior prediction. In _Proceedings of The Web Conference 2020_ (pp. 3056-3062).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.07993) | WWW | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FAutumn945\u002FMGNN-SPred) |\n| MGNN | [Zhang, W., Mao, J., Cao, Y., & Xu, C. (2020, October). Multiplex Graph Neural Networks for Multi-behavior Recommendation. In _Proceedings of the 29th ACM International Conference on Information & Knowledge Management_ (pp. 2313-2316).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412119) | CIKM | 2020 | NA |\n| LP-MRGNN | [Wang, W., Zhang, W., Liu, S., Liu, Q., Zhang, B., Lin, L., & Zha, H. (2021). Incorporating Link Prediction into Multi-Relational Item Graph Modeling for Session-based Recommendation. _IEEE Transactions on Knowledge and Data Engineering_.](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9536374\u002F) | TKDE | 2021 | NA |\n| GNMR | [Xia, L., Huang, C., Xu, Y., Dai, P., Lu, M., & Bo, L. (2021, April). Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling. In _2021 IEEE 37th International Conference on Data Engineering (ICDE)_ (pp. 1931-1936). IEEE.](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458929) | ICDE | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FGNMR) |\n| MB-GMN | [Xia, L., Xu, Y., Huang, C., Dai, P., & Bo, L. (2021, July). Graph meta network for multi-behavior recommendation. In _Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval_ (pp. 757-766).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3404835.3462972) | SIGIR | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FMB-GMN) |\n| KHGT | [Xia, L., Huang, C., Xu, Y., Dai, P., Zhang, X., Yang, H., ... & Bo, L. (2021, May). Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation. In _Proceedings of the AAAI Conference on Artificial Intelligence_ (Vol. 35, No. 5, pp. 4486-4493).](https:\u002F\u002Fwww.aaai.org\u002FAAAI21Papers\u002FAAAI-3071.XiaL.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FKHGT) |\n| GHCF | [Chen, C., Ma, W., Zhang, M., Wang, Z., He, X., Wang, C., ... & Ma, S. (2021, May). Graph Heterogeneous Multi-Relational Recommendation. In _Proceedings of the AAAI Conference on Artificial Intelligence_ (Vol. 35, No. 5, pp. 3958-3966).](https:\u002F\u002Fwww.aaai.org\u002FAAAI21Papers\u002FAAAI-615.ChenC.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fchenchongthu\u002FGHCF) |\n| DMBGN | [Xiao, F., Li, L., Xu, W., Zhao, J., Yang, X., Lang, J., & Wang, H. (2021). DMBGN: Deep Multi-Behavior Graph Networks for Voucher Redemption Rate Prediction. _arXiv preprint arXiv:2106.03356_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.03356) | KDD | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ffengtong-xiao\u002FDMBGN) |\n| HMG-CR | [Yang, H., Chen, H., Li, L., Yu, P. S., & Xu, G. (2021). Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation. _arXiv preprint arXiv:2109.02859_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.02859) | ICDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FHaoran-Young\u002FHMG-CR) |\n| GNNH | [Yu, B., Zhang, R., Chen, W., & Fang, J. (2021). Graph neural network based model for multi-behavior session-based recommendation. _GeoInformatica_, 1-19.](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10707-021-00439-w) | GeoInformatica | 2021 | NA |\n\n### Diversity\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| V2HT | [Li, M., Gan, T., Liu, M., Cheng, Z., Yin, J., & Nie, L. (2019, November). Long-tail hashtag recommendation for micro-videos with graph convolutional network. In _Proceedings of the 28th ACM International Conference on Information and Knowledge Management_ (pp. 509-518).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3357912) | CIKM | 2019 | NA |\n| BGCF | [Sun, J., Guo, W., Zhang, D., Zhang, Y., Regol, F., Hu, Y., ... & Coates, M. (2020, August). A framework for recommending accurate and diverse items using bayesian graph convolutional neural networks. In _Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining_ (pp. 2030-2039).](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FJianing-Sun-5\u002Fpublication\u002F343780326_A_Framework_for_Recommending_Accurate_and_Diverse_Items_Using_Bayesian_Graph_Convolutional_Neural_Networks\u002Flinks\u002F5f85d507299bf1b53e23724f\u002FA-Framework-for-Recommending-Accurate-and-Diverse-Items-Using-Bayesian-Graph-Convolutional-Neural-Networks.pdf) | KDD | 2020 | [Python](https:\u002F\u002Fgitee.com\u002Fmindspore\u002Fmodels\u002Ftree\u002Fmaster\u002Fofficial\u002Fgnn\u002Fbgcf) |\n| DGCN | [Zheng, Y., Gao, C., Chen, L., Jin, D., & Li, Y. (2021, April). DGCN: Diversified Recommendation with Graph Convolutional Networks. In _Proceedings of the Web Conference 2021_ (pp. 401-412).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2108.06952.pdf) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FDGCN) |\n| FH-HAT | [Xie, R., Liu, Q., Liu, S., Zhang, Z., Cui, P., Zhang, B., & Lin, L. (2021). Improving Accuracy and Diversity in Matching of Recommendation with Diversified Preference Network. arXiv preprint arXiv:2102.03787.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.03787) | TBD | 2021 | NA |\n| Isufi _et al._ | [Isufi, E., Pocchiari, M., & Hanjalic, A. (2021). Accuracy-diversity trade-off in recommender systems via graph convolutions. _Information Processing & Management_, _58_(2), 102459.](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0306457320309511) | IPM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fesilezz\u002Faccdiv-via-graphconv) |\n\n### Explainability\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| RippleNet | [Wang, H., Zhang, F., Wang, J., Zhao, M., Li, W., Xie, X., & Guo, M. (2018, October). Ripplenet: Propagating user preferences on the knowledge graph for recommender systems. In _Proceedings of the 27th ACM International Conference on Information and Knowledge Management_ (pp. 417-426).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.03467) | CIKM | 2018 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fripplenet-propagating-user-preferences-on-the) |\n| EIUM | [Huang, X., Fang, Q., Qian, S., Sang, J., Li, Y., & Xu, C. (2019, October). Explainable interaction-driven user modeling over knowledge graph for sequential recommendation. In _Proceedings of the 27th ACM International Conference on Multimedia_ (pp. 548-556).](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3343031.3350893) | MM | 2019 | NA |\n| KPRN | [Wang, X., Wang, D., Xu, C., He, X., Cao, Y., & Chua, T. S. (2019, July). Explainable reasoning over knowledge graphs for recommendation. In _Proceedings of the AAAI Conference on Artificial Intelligence_ (Vol. 33, No. 01, pp. 5329-5336).](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4470\u002F4348) | AAAI | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fexplainable-reasoning-over-knowledge-graphs) |\n| RuleRec | [Ma, W., Zhang, M., Cao, Y., Jin, W., Wang, C., Liu, Y., ... & Ren, X. (2019, May). Jointly learning explainable rules for recommendation with knowledge graph. In _The World Wide Web Conference_ (pp. 1210-1221).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.03714) | WWW | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FTHUIR\u002FRuleRec) |\n| PGPR | [Xian, Y., Fu, Z., Muthukrishnan, S., De Melo, G., & Zhang, Y. (2019, July). Reinforcement knowledge graph reasoning for explainable recommendation. In _Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval_ (pp. 285-294).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.05237) | SIGIR | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Forcax\u002FPGPR) |\n| KGAT | [Wang, X., He, X., Cao, Y., Liu, M., & Chua, T. S. (2019, July). Kgat: Knowledge graph attention network for recommendation. In _Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining_ (pp. 950-958).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.07854) | KDD | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fkgat-knowledge-graph-attention-network-for) |\n| TMER | [Chen, H., Li, Y., Sun, X., Xu, G., & Yin, H. (2021, March). Temporal meta-path guided explainable recommendation. In _Proceedings of the 14th ACM International Conference on Web Search and Data Mining_ (pp. 1056-1064).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2101.01433) | WSDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FAbigale001\u002FTMER) |\n| ECFKG | [Bose, A., & Hamilton, W. (2019, May). Compositional fairness constraints for graph embeddings. In _International Conference on Machine Learning_ (pp. 715-724). PMLR.](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fbose19a\u002Fbose19a.pdf) | ICML | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fjoeybose\u002FFlexible-Fairness-Constraints) |\n| HAGERec | [Yang, Z., & Dong, S. (2020). HAGERec: hierarchical attention graph convolutional network incorporating knowledge graph for explainable recommendation. _Knowledge-Based Systems_, _204_, 106194.](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0950705120304196) | KBS | 2020 | NA |\n\n### Fairness\n| **Name** | **Paper** | **Venue** | **Year** | **Code** |\n| --- | --- | --- | --- | --- |\n| FairGo | [Wu, L., Chen, L., Shao, P., Hong, R., Wang, X., & Wang, M. (2021, April). Learning Fair Representations for Recommendation: A Graph-based Perspective. In _Proceedings of the Web Conference 2021_ (pp. 2198-2208).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.09140) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fnewlei\u002FFairGo) |\n| FairGNN | [Dai, E., & Wang, S. (2021, March). Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In _Proceedings of the 14th ACM International Conference on Web Search and Data Mining_ (pp. 680-688).](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.01454) | WSDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FEnyanDai\u002FFairGNN) |\n| Fairwalk | [Rahman, T., Surma, B., Backes, M., & Zhang, Y. (2019). Fairwalk: Towards fair graph embedding.](https:\u002F\u002Fpublications.cispa.saarland\u002F2933\u002F1\u002FIJCAI19.pdf) | IJCAI | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Ffairwalk-towards-fair-graph-embedding) |\n| CFCGE | [Bose, A., & Hamilton, W. (2019, May). Compositional fairness constraints for graph embeddings. In _International Conference on Machine Learning_ (pp. 715-724). PMLR.](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fbose19a\u002Fbose19a.pdf) | ICML | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fjoeybose\u002FFlexible-Fairness-Constraints) |\n\n","# 基于图神经网络的推荐系统\n一个基于图神经网络的推荐算法索引。\n\n我们的综述《面向推荐系统的图神经网络综述：挑战、方法与方向》已被 ACM 推荐系统汇刊（ACM Transactions on Recommender Systems）接收。\n预印本已在 arXiv 上发布：[链接](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.12843v2.pdf)\n\n如果本索引对您有所帮助，请引用我们的综述论文：\n```\n@article{gao2022survey,\n  title={A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions},\n  author={Gao, Chen and Zheng, Yu and Li, Nian and Li, Yinfeng and Qin, Yingrong and Piao, Jinghua and Quan, Yuhan and Chang, Jianxin and Jin, Depeng and He, Xiangnan and Li, Yong},\n  journal={ACM Transactions on Recommender Systems (TORS)},\n  year={2022}\n}\n```\n```\nGao, C., Zheng, Y., Li, N., Li, Y., Qin, Y., Piao, J., Quan, Y., Chang, J., Jin, D., He, X., & Li, Y. (2022). 面向推荐系统的图神经网络综述：挑战、方法与方向。ACM 推荐系统汇刊（TORS）。\n```\n\n# 目录\n\n- [不同推荐阶段中的图神经网络](#Recommendation-Stages)\n   - [匹配](#Matching)\n   - [排序](#Ranking)\n   - [重排序](#Re-ranking)\n- [不同推荐场景中的图神经网络](#Recommendation-Scenarios)\n   - [社交推荐](#Social-Recommendation)\n   - [序列推荐](#Sequential-Recommendation)\n   - [会话推荐](#Session-Recommendation)\n   - [捆绑推荐](#Bundle-Recommendation)\n   - [跨域推荐](#Cross-Domain-Recommendation)\n- [针对不同推荐目标的图神经网络](#Recommendation-Objectives)\n   - [多行为推荐](#Multi-behavior-Recommendation)\n   - [多样性](#Diversity)\n   - [可解释性](#Explainability)\n   - [公平性](#Fairness)\n## 推荐阶段\n### 匹配\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| GCMC | [Berg, R. V. D., Kipf, T. N., & Welling, M. (2017). 图卷积矩阵补全。_arXiv 预印本 arXiv:1706.02263_.](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.02263.pdf) | arxiv | 2017 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fgraph-convolutional-matrix-completion) |\n| Pin-Sage | [Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., & Leskovec, J. (2018年7月). 面向大规模推荐系统的图卷积神经网络。载于第24届 ACM SIGKDD 国际知识发现与数据挖掘大会论文集（pp. 974–983）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1806.01973) | KDD | 2018 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fgraph-convolutional-neural-networks-for-web) |\n| NGCF | [Wang, X., He, X., Wang, M., Feng, F., & Chua, T. S. (2019年7月). 神经图协同过滤。载于第42届国际 ACM SIGIR 信息检索研究与发展大会论文集（pp. 165–174）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.08108.pdf) | SIGIR | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fneural-graph-collaborative-filtering) |\n| LightGCN | [He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., & Wang, M. (2020年7月). LightGCN：简化并增强用于推荐的图卷积网络。载于第43届国际 ACM SIGIR 信息检索研究与发展大会论文集（pp. 639–648）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.02126.pdf) | SIGIR | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Flightgcn-simplifying-and-powering-graph) |\n| NIA-GCN | [Sun, J., Zhang, Y., Guo, W., Guo, H., Tang, R., He, X., ... & Coates, M. (2020年7月). 考虑邻居交互的图卷积网络用于推荐。载于第43届国际 ACM SIGIR 信息检索研究与发展大会论文集（pp. 1289–1298）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3397271.3401123) | SIGIR | 2020 | 无 |\n| DGCF | [Wang, X., Jin, H., Zhang, A., He, X., Xu, T., & Chua, T. S. (2020年7月). 解耦图协同过滤。载于第43届国际 ACM SIGIR 信息检索研究与发展大会论文集（pp. 1001–1010）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.01764) | SIGIR | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fdisentangled-graph-collaborative-filtering) |\n| IMP-GCN | [Liu, F., Cheng, Z., Zhu, L., Gao, Z., & Nie, L. (2021年4月). 关注兴趣的消息传递图卷积网络用于推荐。载于 2021 年万维网大会论文集（pp. 1296–1305）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.10044.pdf) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fliufancs\u002FIMP_GCN) |\n| SGL | [Wu, J., Wang, X., Feng, F., He, X., Chen, L., Lian, J., & Xie, X. (2021年7月). 自监督图学习用于推荐。载于第44届国际 ACM SIGIR 信息检索研究与发展大会论文集（pp. 726–735）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.10783) | SIGIR | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fwujcan\u002FSGL) |\n| LT-OCF | [Choi, J., Jeon, J., & Park, N. (2021). LT-OCF：基于可学习时间常数的 ODE 协同过滤。载于第30届 ACM 国际信息与知识管理大会论文集（pp. 251–260）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3459637.3482449) | CIKM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FLT-OCF) |\n| HMLET | [Kong, T., Kim, T., Jeon, J., Choi, J., Lee, Y-C., Park, N., & Kim, S-W. (2022). 线性还是非线性，这就是问题！载于第15届 ACM 国际网页搜索与数据挖掘大会论文集（pp. 517–525）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3488560.3498501) | WSDM | 2022 | [Python](https:\u002F\u002Fgithub.com\u002Fjeongwhanchoi\u002FHMLET) |\n| HS-GCN | [Liu, H., Wei, Y., Yin, J., & Nie, L. (2022). HS-GCN：用于推荐的汉明空间图卷积网络。IEEE 知识与数据工程汇刊。](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9732648) | TKDE | 2022 | [Python](https:\u002F\u002Fgithub.com\u002Fhanliu95\u002FHS-GCN) |\n| LGCN | [Yu, W., Zhang, Z., & Qin, Z. (2022). 低通图卷积网络用于推荐。](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-3643.WenhuiY.pdf) | AAAI | 2022 | [Python](https:\u002F\u002Fgithub.com\u002FWenhui-Yu\u002FLCFN) |\n\n### 排名\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| Fi-GNN | [Li, Z., Cui, Z., Wu, S., Zhang, X., & Wang, L. (2019年11月). Fi-gnn：通过图神经网络建模特征交互以进行点击率预测。载于《第28届ACM国际信息与知识管理会议论文集》（第539–548页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.05552.pdf) | CIKM | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Ffi-gnn-modeling-feature-interactions-via) |\n| PUP | [Zheng, Y., Gao, C., He, X., Li, Y., & Jin, D. (2020年4月). 基于图卷积网络的价格感知推荐。载于《2020 IEEE 第36届国际数据工程会议（ICDE）》（第133–144页）。IEEE。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2003.03975.pdf) | ICDE | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FDavyMorgan\u002FICDE20-PUP) |\n| A2-GCN | [Liu, F., Cheng, Z., Zhu, L., Liu, C., & Nie, L. (2020). A2-GCN：一种用于推荐的属性感知注意力GCN模型。IEEE知识与数据工程汇刊。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2003.09086.pdf) | TKDE | 2020 | 无 |\n| L\u003Csub>0\u003C\u002Fsub>-SIGN | [Su, Y., Zhang, R., Erfani, S., & Xu, Z. (2021年5月). 检测推荐系统中有益的特征交互。载于《第34届AAAI人工智能会议论文集》。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.00404.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fruizhang-ai\u002FSIGN-Detecting-Beneficial-Feature-Interactions-for-Recommender-Systems) |\n| DG-ENN | [Guo, W., Su, R., Tan, R., Guo, H., Zhang, Y., Liu, Z., ... & He, X. (2021). 双图增强嵌入神经网络用于点击率预测。_arXiv预印本 arXiv:2106.00314_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.00314.pdf) | KDD | 2021 | 无 |\n| SHCF | [Li, C., Hu, L., Shi, C., Song, G., & Lu, Y. (2021). 序列感知异构图神经协同过滤。载于《2021 SIAM国际数据挖掘会议论文集》（第64–72页）。工业与应用数学学会。](http:\u002F\u002Fwww.shichuan.org\u002Fdoc\u002F98.pdf) | SDM | 2021 | [Python](http:\u002F\u002Fwww.shichuan.org\u002Fdataset\u002FSHCF.zip) |\n| GCM | [Wu, J., He, X., Wang, X., Wang, Q., Chen, W., Lian, J., & Xie, X. (2020). 上下文感知推荐系统的图卷积机器。_arXiv预印本 arXiv:2001.11402_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.11402.pdf) | 计算机科学前沿 | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fwujcan\u002FGCM) |\n| TGIN | [Jiang, W., Jiao, Y., Wang, Q., Liang, C., Guo, L., Zhang, Y., ... & Zhu, Y. (2022年2月). 三角图兴趣网络用于点击率预测。载于《第十五届ACM国际网络搜索与数据挖掘会议论文集》（第401–409页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.02698.pdf) | WSDM | 2022 | [Python](https:\u002F\u002Fgithub.com\u002Falibaba\u002Ftgin) |\n\n### 重新排名\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| IRGPR | [Liu, W., Liu, Q., Tang, R., Chen, J., He, X., & Heng, P. A. (2020年10月). 面向电子商务的商品关系个性化重排序。载于《第29届ACM国际信息与知识管理会议论文集》（第925–934页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412332) | CIKM | 2020 | 无 |\n\n## 推荐场景\n\n### 社交推荐\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| DiffNet | [Wu, L., Sun, P., Fu, Y., Hong, R., Wang, X., & Wang, M. (2019年7月). 一种用于社交推荐的神经影响力扩散模型。载于《第42届国际ACM SIGIR信息检索研究与发展会议论文集》（pp. 235-244）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.10322) | SIGIR | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fa-neural-influence-diffusion-model-for-social) |\n| GraphRec | [Fan, W., Ma, Y., Li, Q., He, Y., Zhao, E., Tang, J., & Yin, D. (2019年5月). 用于社交推荐的图神经网络。载于《万维网大会》（pp. 417-426）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.07243) | WWW | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fgraph-neural-networks-for-social) |\n| DANSER | [Wu, Q., Zhang, H., Gao, X., He, P., Weng, P., Gao, H., & Chen, G. (2019年5月). 用于推荐系统中多面社会效应深度潜在表示的双图注意力网络。载于《万维网大会》（pp. 2091-2102）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.10433) | WWW | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fqitianwu\u002FDANSER-WWW-19) |\n| DGRec | [Song, W., Xiao, Z., Wang, Y., Charlin, L., Zhang, M., & Tang, J. (2019年1月). 基于会话的社交推荐：利用动态图注意力网络。载于《第十二届ACM国际网络搜索与数据挖掘会议论文集》（pp. 555-563）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.09362) | WSDM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FRecommenderSystems) |\n| HGP | [Kim, K. M., Kwak, D., Kwak, H., Park, Y. J., Sim, S., Cho, J. H., ... & Ha, J. W. (2019). 用于大规模社交推荐的三方异质图传播。_arXiv预印本 arXiv:1908.02569_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.02569) | RecSys | 2019 | 无 |\n| DiffNet++ | [Wu, L., Li, J., Sun, P., Hong, R., Ge, Y., & Wang, M. (2020). Diffnet++：一种用于社交推荐的神经影响力与兴趣扩散网络。IEEE知识与数据工程汇刊。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.00844.pdf) | TKDE | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fdiffnet-a-neural-influence-and-interest) |\n| MHCN | [Yu, J., Yin, H., Li, J., Wang, Q., Hung, N. Q. V., & Zhang, X. (2021年4月). 用于社交推荐的自监督多通道超图卷积网络。载于《2021年万维网大会论文集》（pp. 413-424）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2101.06448) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FCoder-Yu\u002FQRec) |\n| SEPT | [Yu, J., Yin, H., Gao, M., Xia, X., Zhang, X., & Hung, N. Q. V. (2021). 具有社交感知的自监督三重训练用于推荐。_arXiv预印本 arXiv:2106.03569_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.03569) | KDD | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FCoder-Yu\u002FQRec) |\n| GBGCN | [Zhang, J., Gao, C., Jin, D., & Li, Y. (2021年4月). 面向社交电商的团购推荐。载于《2021年IEEE第37届国际数据工程会议（ICDE）》（pp. 1536-1547）。IEEE。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.06848) | ICDE | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FSweetnow\u002Fgroup-buying-recommendation) |\n| KCGN | [Huang, C., Xu, H., Xu, Y., Dai, P., Xia, L., Lu, M., ... & Ye, Y. (2021年1月). 具有知识感知的耦合图神经网络用于社交推荐。载于《AAAI人工智能会议》。](https:\u002F\u002Fwww.aaai.org\u002FAAAI21Papers\u002FAAAI-9069.HuangC.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fxhcdream\u002FKCGN) |\n| DiffNetLG | [Song, C., Wang, B., Jiang, Q., Zhang, Y., He, R., & Hou, Y. (2021年7月). 考虑隐性社会影响力的社交推荐。载于《第44届国际ACM SIGIR信息检索研究与发展会议论文集》（pp. 1788-1792）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3404835.3463043) | SIGIR | 2021 | 无 |\n| RecoGCN | [Xu, F., Lian, J., Han, Z., Li, Y., Xu, Y., & Xie, X. (2019年11月). 关系感知的图卷积网络用于代理发起的社交电商推荐。载于《第28届ACM国际信息与知识管理会议论文集》（pp. 529-538）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3357384.3357924) | CIKM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fxfl15\u002FRecoGCN) |\n| GAT-NSR | [Mu, N., Zha, D., He, Y., & Tang, Z. (2019年11月). 图注意力网络用于神经网络社交推荐。载于《2019年IEEE第31届人工智能工具国际会议（ICTAI）》（pp. 1320-1327）。IEEE。](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8995280) | ICTAI | 2019 | 无 |\n| SR-HGNN | [Xu, H., Huang, C., Xu, Y., Xia, L., Xing, H., & Yin, D. (2020年11月). 利用层次化图神经网络增强全局上下文的社交推荐。载于《2020年IEEE国际数据挖掘会议（ICDM）》（pp. 701-710）。IEEE。](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9338365) | ICDM | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fxhcdream\u002FSR-HGNN) |\n| TGRec | [Bai, T., Zhang, Y., Wu, B., & Nie, J. Y. (2020年12月). 用于社交推荐的时序图神经网络。载于《2020年IEEE国际大数据会议（Big Data）》（pp. 898-903）。IEEE。](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9378444) | ICBD | 2020 | 无 |\n| ESRF | [Yu, J., Yin, H., Li, J., Gao, M., Huang, Z., & Cui, L. (2020). 利用对抗性图卷积网络增强社交推荐。_IEEE知识与数据工程汇刊_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.02340) | TKDE | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FCoder-Yu\u002FQRec) |\n| HOSR | [Liu, Y., Liang, C., He, X., Peng, J., Zheng, Z., & Tang, J. (2020). 为物品推荐建模高阶社会关系。_IEEE知识与数据工程汇刊_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2003.10149) | TKDE | 2020 | 无 |\n| GNN-SoR | [Guo, Z., & Wang, H. (2020). 一种基于深度图神经网络的社交推荐机制。_IEEE工业信息学汇刊_，第17卷第4期，2776-2783页。](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9063418) | TII | 2020 | 无 |\n| ASR | [Luo, D., Bian, Y., Zhang, X., & Huan, J. (2020). 注意力导向的社交推荐：面向用户和物品多样性。_arXiv预印本 arXiv:2011.04797_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.04797) | arXiv | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fflyingdoog\u002FASR) |\n\n### 顺序推荐\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| ISSR | [Liu, F., Liu, W., Li, X., & Ye, Y. (2020). 面向个性化顺序推荐的序列间增强框架。_arXiv预印本 arXiv:2004.12118_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12118) | AAAI | 2020 | 无 |\n| MA-GNN | [Ma, C., Ma, L., Zhang, Y., Sun, J., Liu, X., & Coates, M. (2020年4月). 用于顺序推荐的内存增强图神经网络。载于《AAAI人工智能会议论文集》（第34卷，第04期，页5045–5052）。](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fdownload\u002F5945\u002F5801) | AAAI | 2020 | 无 |\n| STP-UDGAT | [Lim, N., Hooi, B., Ng, S. K., Wang, X., Goh, Y. L., Weng, R., & Varadarajan, J. (2020年10月). STP-UDGAT：面向下一站POI推荐的时空偏好用户维度图注意力网络。载于《第29届ACM国际信息与知识管理会议论文集》（页845–854）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.07024) | CIKM | 2020 | 无 |\n| GPR | [Chang, B., Jang, G., Kim, S., & Kang, J. (2020年10月). 基于图的地理潜在表示学习用于兴趣点推荐。载于《第29届ACM国际信息与知识管理会议论文集》（页135–144）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3411905) | CIKM | 2020 | 无 |\n| GES-SASRec | [Zhu, T., Sun, L., & Chen, G. (2021). 用于顺序推荐的基于图的嵌入平滑方法。_IEEE知识与数据工程汇刊_。](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9405450\u002F) | TKDE | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fzhuty16\u002FGES) |\n| RetaGNN | [Hsu, C., & Li, C. T. (2021年4月). RetaGNN：面向整体顺序推荐的关联时间注意力图神经网络。载于《Web Conference 2021会议论文集》（页2968–2979）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2101.12457) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fretagnn\u002FRetaGNN) |\n| TGSRec | [Fan, Z., Liu, Z., Zhang, J., Xiong, Y., Zheng, L., & Yu, P. S. (2021). 基于时间图协同Transformer的连续时间顺序推荐。_arXiv预印本 arXiv:2108.06625_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2108.06625) | CIKM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FDyGRec\u002FTGSRec) |\n| SGRec | [Li, Y., Chen, T., Yin, H., & Huang, Z. (2021). 利用迭代Seq2Graph增强发现用于下一站POI推荐的协同信号。_arXiv预印本 arXiv:2106.15814_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.15814) | IJCAI | 2021 | 无 |\n| SURGE | [Chang, J., Gao, C., Zheng, Y., Hui, Y., Niu, Y., Song, Y., ... & Li, Y. (2021年7月). 基于图神经网络的顺序推荐。载于《第44届国际ACM SIGIR信息检索研究与发展会议论文集》（页378–387）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.14226) | SIGIR | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FSIGIR21-SURGE) |\n| GME | [Xie, M., Yin, H., Xu, F., Wang, H., & Zhou, X. (2016年11月). 基于图度量嵌入的下一站POI推荐。载于《国际Web信息系统工程会议论文集》（页207–222）。Springer, Cham。](http:\u002F\u002Fnet.pku.edu.cn\u002Fdaim\u002Fhongzhi.yin\u002Fpapers\u002FWISE-2016.pdf) | WISE | 2016 | 无 |\n| Wang _et al._ | [Wang, B., & Cai, W. (2020). 知识增强的图神经网络用于顺序推荐。_Information_, _11_(8), 388。](https:\u002F\u002Fwww.mdpi.com\u002F2078-2489\u002F11\u002F8\u002F388\u002Fpdf) | Information | 2020 | 无 |\n| DGSR | [Zhang, M., Wu, S., Yu, X., & Wang, L. (2021). 用于顺序推荐的动态图神经网络。_arXiv预印本 arXiv:2104.07368_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2104.07368) | arXiv | 2021 | 无 |\n\n### 会话推荐\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| SR-GNN | [Wu, S., Tang, Y., Zhu, Y., Wang, L., Xie, X., & Tan, T. (2019年7月). 基于图神经网络的会话推荐。载于《AAAI人工智能会议论文集》（第33卷，第01期，第346–353页）。](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F3804\u002F3682) | AAAI | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fsession-based-recommendation-with-graph) |\n| GC-SAN | [Xu, C., Zhao, P., Liu, Y., Sheng, V. S., Xu, J., Zhuang, F., ... & Zhou, X. (2019年8月). 用于会话推荐的图上下文自注意力网络。载于《IJCAI》（第19卷，第3940–3946页）。](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2019\u002F0547.pdf) | IJCAI | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FRUCAIBox\u002FRecBole\u002Fblob\u002Fmaster\u002Frecbole\u002Fmodel\u002Fsequential_recommender\u002Fgcsan.py) |\n| TA-GNN | [Yu, F., Zhu, Y., Liu, Q., Wu, S., Wang, L., & Tan, T. (2020年7月). TAGNN：面向会话推荐的目标感知图神经网络。载于《第43届国际ACM SIGIR信息检索研究与发展会议论文集》（第1921–1924页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.02844) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FTAGNN) |\n| MGNN-SPred | [Wang, W., Zhang, W., Liu, S., Liu, Q., Zhang, B., Lin, L., & Zha, H. (2020年4月). 超越点击：基于多关系物品图的会话目标行为预测建模。载于《The Web Conference 2020论文集》（第3056–3062页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.07993) | WWW | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FAutumn945\u002FMGNN-SPred) |\n| LESSR | [Chen, T., & Wong, R. C. W. (2020年8月). 处理会话推荐中图神经网络的信息损失问题。载于《第26届ACM SIGKDD国际知识发现与数据挖掘会议论文集》（第1172–1180页）。](http:\u002F\u002Fhome.cse.ust.hk\u002F~raywong\u002Fpaper\u002Fkdd20-informationLoss-GNN.pdf) | KDD | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Ftwchen\u002Flessr) |\n| MKM-SR | [Meng, W., Yang, D., & Xiao, Y. (2020年7月). 将用户微观行为和物品知识融入多任务学习以进行会话推荐。载于《第43届国际ACM SIGIR信息检索研究与发展会议论文集》（第1091–1100页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.06922) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fciecus\u002FMKM-SR) |\n| GAG | [Qiu, R., Yin, H., Huang, Z., & Chen, T. (2020年7月). Gag：用于流式会话推荐的全局属性图神经网络。载于《第43届国际ACM SIGIR信息检索研究与发展会议论文集》（第669–678页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.02747) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FRuihongQiu\u002FGAG) |\n| GCE-GNN | [Wang, Z., Wei, W., Cong, G., Li, X. L., Mao, X. L., & Qiu, M. (2020年7月). 全局上下文增强的图神经网络用于会话推荐。载于《第43届国际ACM SIGIR信息检索研究与发展会议论文集》（第169–178页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.05081) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FCCIIPLab\u002FGCE-GNN) |\n| SGNN-HN | [Pan, Z., Cai, F., Chen, W., Chen, H., & de Rijke, M. (2020年10月). 星型图神经网络用于会话推荐。载于《第29届ACM国际信息与知识管理会议论文集》（第1195–1204页）。](https:\u002F\u002Firlab.science.uva.nl\u002Fwp-content\u002Fpapercite-data\u002Fpdf\u002Fpan-2020-star.pdf) | CIKM | 2020 | 无 |\n| DHCN | [Xia, X., Yin, H., Yu, J., Wang, Q., Cui, L., & Zhang, X. (2020年）。用于会话推荐的自监督超图卷积网络。_arXiv预印本 arXiv:2012.06852_。](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F16578) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fxiaxin1998\u002FDHCN) |\n| SHARE | [Wang, J., Ding, K., Zhu, Z., & Caverlee, J. (2021年）。利用超图注意力网络进行会话推荐。载于《2021年SIAM国际数据挖掘会议（SDM）论文集》（第82–90页）。工业与应用数学学会。](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fpdf\u002F10.1137\u002F1.9781611976700.10) | SDM | 2021 | 无 |\n| SERec | [Chen, T., & Wong, R. C. W. (2021年3月）。一种高效且有效的会话社交推荐框架。载于《第14届ACM国际网络搜索与数据挖掘会议论文集》（第400–408页）。](http:\u002F\u002Fwww.cse.ust.hk\u002F~raywong\u002Fpaper\u002Fwsdm21-SEFrame.pdf) | WSDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ftwchen\u002FSEFrame) |\n| COTREC | [Xia, X., Yin, H., Yu, J., Shao, Y., & Cui, L. (2021年）。用于会话推荐的自监督图协同训练。arXiv预印本 arXiv:2108.10560。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2108.10560) | CIKM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fxiaxin1998\u002FCOTREC) |\n| DAT-MDI | [Chen, C., Guo, J., & Song, B. (2021年7月）。在会话推荐中实现多维度融合的双重注意力转移。载于《第44届国际ACM SIGIR信息检索研究与发展会议论文集》（第869–878页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3404835.3462866) | SIGIR | 2021 | 无 |\n| TASRec | [Zhou, H., Tan, Q., Huang, X., Zhou, K., & Wang, X. (2021年）。用于会话推荐的时间增强图神经网络。](https:\u002F\u002Fwww4.comp.polyu.edu.hk\u002F~xiaohuang\u002Fdocs\u002FHuachi_sigir2021.pdf) | SIGIR | 2021 | 无 |\n| G\u003Csup>3\u003C\u002Fsup>SR | [Deng, Z. H., Wang, C. D., Huang, L., Lai, J. H., & Philip, S. Y. (2022年）。G^3SR：全球图引导的会话推荐。IEEE神经网络与学习系统汇刊。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2203.06467.pdf) | TNNLS | 2022 | 无 |\n| HG-GNN | [Pang, Y., Wu, L., Shen, Q., Zhang, Y., Wei, Z., Xu, F., ... & Pei, J. (2022年2月）。用于个性化会话推荐的异构全局图神经网络。载于《第十五届ACM国际网络搜索与数据挖掘会议论文集》（第775–783页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2107.03813.pdf) | WSDM | 2022 | [Python](https:\u002F\u002Fgithub.com\u002F0215Arthur\u002FHG-GNN) |\n| CGL | [Pan, Z., Cai, F., Chen, W., Chen, C., & Chen, H. (2022年）。用于会话推荐的协作图学习。ACM信息系统汇刊（TOIS），第40卷第4期，第1–26页。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3490479) | TOIS | 2022 | 无 |\n| CAGE | [Sheu, H. S., & Li, S. (2020年9月）。面向会话新闻推荐的上下文感知图嵌入。载于《第十四届ACM推荐系统会议论文集》（第657–662页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3383313.3418477) | RecSys | 2020 | 无 |\n| A-PGNN | [Zhang, M., Wu, S., Gao, M., Jiang, X., Xu, K., & Wang, L. (2020年）。具有注意力机制的个性化图神经网络，用于会话感知推荐。IEEE知识与数据工程汇刊。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.08887) | TKDE | 2020 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fpersonalizing-graph-neural-networks-with) |\n| DGTN | [Zheng, Y., Liu, S., Li, Z., & Wu, S. (2020年11月）。DGTN：用于会话推荐的双通道图转换网络。载于《2020年国际数据挖掘研讨会（ICDMW）论文集》（第236–242页）。IEEE。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.10002) | ICDMW | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fkunwuz\u002FDGTN) |\n| FGNN | [Qiu, R., Li, J., Huang, Z., & Yin, H. (2019年11月）。利用图神经网络重新思考会话推荐中的物品顺序。载于《第28届ACM国际信息与知识管理会议论文集》（第579–588页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.11942) | CIKM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FRuihongQiu\u002FFGNN) |\n\n### 捆绑推荐\n| **名称** | **论文** | **会议** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| BGCN | [Chang, J., Gao, C., He, X., Jin, D., & Li, Y. (2020年7月). 基于图卷积网络的捆绑推荐。载于《第43届国际ACM SIGIR信息检索研究与发展会议论文集》（第1673–1676页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.03475) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fcjx0525\u002FBGCN) |\n| HFGN | [Li, X., Wang, X., He, X., Chen, L., Xiao, J., & Chua, T. S. (2020年7月). 用于个性化穿搭推荐的层次化时尚图网络。载于《第43届国际ACM SIGIR信息检索研究与发展会议论文集》（第159–168页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.12566) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fxcppy\u002Fhierarchical_fashion_graph_network) |\n| BundleNet | [Deng, Q., Wang, K., Zhao, M., Zou, Z., Wu, R., Tao, J., ... & Chen, L. (2020年10月). 在线游戏中个性化的捆绑推荐。载于《第29届ACM国际信息与知识管理会议论文集》（第2381–2388页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2104.05307) | CIKM | 2020 | 无 |\n| DPR | [Zheng, Z., Wang, C., Xu, T., Shen, D., Qin, P., Huai, B., ... & Chen, E. (2021年4月). 基于交互感知图归纳的药品包装推荐。载于《Web Conference 2021论文集》（第1284–1295页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.03577) | WWW | 2021 | 无 |\n| DPG | [Zheng, Z., Wang, C., Xu, T., Shen, D., Qin, P., Zhao, X., ... & Chen, E. (2022年). 基于策略梯度的交互感知药品包装推荐。ACM信息系统事务期刊（TOIS）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3511020) | TOIS | 2022 | 无 |\n| MIDGN | [Zhao, S., Wei, W., Zou, D., & Mao, X. (2022年). 用于捆绑推荐的多视角意图解耦图网络。arXiv预印本，arXiv:2202.11425。](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F20359) | AAAI | 2022 | [Python](https:\u002F\u002Fgithub.com\u002FSnnzhao\u002FMIDGN) |\n\n### 跨领域推荐\n| **名称** | **论文** | **会议** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| PPGN | [Zhao, C., Li, C., & Fu, C. (2019年11月). 基于偏好传播图网络的跨领域推荐。载于《第28届ACM国际信息与知识管理会议论文集》（第2165–2168页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3358166) | CIKM | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FWHUIR\u002FPPGN) |\n| BiTGCF | [Liu, M., Li, J., Li, G., & Pan, P. (2020年10月). 基于双向迁移图协同过滤网络的跨领域推荐。载于《第29届ACM国际信息与知识管理会议论文集》（第885–894页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412012) | CIKM | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fsunshinelium\u002FBi-TGCF) |\n| DAN | [Wang, B., Zhang, C., Zhang, H., Lyu, X., & Tang, Z. (2020年10月). 具有交换重构功能的双自编码器网络，用于冷启动推荐。载于《第29届ACM国际信息与知识管理会议论文集》（第2249–2252页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412069) | CIKM | 2020 | 无 |\n| HeroGRAPH | [Cui, Q., Wei, T., Zhang, Y., & Zhang, Q. (2020年). HeroGRAPH：一种用于多目标跨领域推荐的异构图框架。载于《ORSUM@ RecSys》。](http:\u002F\u002Fceur-ws.org\u002FVol-2715\u002Fpaper6.pdf) | RecSys | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Fcuiqiang1990\u002FHeroGRAPH) |\n| DAGCN | [Guo, L., Tang, L., Chen, T., Zhu, L., Nguyen, Q. V. H., & Yin, H. (2021年). DA-GCN：一种面向领域的注意力图卷积网络，用于共享账号下的跨领域序列推荐。arXiv预印本，arXiv:2105.03300。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2105.03300) | IJCAI | 2021 | 无 |\n\n## 推荐目标\n\n### 多行为推荐\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| MBGCN | [Jin, B., Gao, C., He, X., Jin, D., & Li, Y. (2020年7月). 利用图卷积网络进行多行为推荐。载于《第43届国际ACM SIGIR信息检索研究与发展会议论文集》（第659–668页）。](http:\u002F\u002Fstaff.ustc.edu.cn\u002F~hexn\u002Fpapers\u002Fsigir20-MBGCN.pdf) | SIGIR | 2020 | [Python](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FMBGCN) |\n| MGNN-SPred | [Wang, W., Zhang, W., Liu, S., Liu, Q., Zhang, B., Lin, L., & Zha, H. (2020年4月). 不止于点击：基于会话的目标行为预测的多关系物品图建模。载于《2020年万维网大会论文集》（第3056–3062页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.07993) | WWW | 2020 | [Python](https:\u002F\u002Fgithub.com\u002FAutumn945\u002FMGNN-SPred) |\n| MGNN | [Zhang, W., Mao, J., Cao, Y., & Xu, C. (2020年10月). 用于多行为推荐的多重图神经网络。载于《第29届ACM国际信息与知识管理会议论文集》（第2313–2316页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3340531.3412119) | CIKM | 2020 | 无 |\n| LP-MRGNN | [Wang, W., Zhang, W., Liu, S., Liu, Q., Zhang, B., Lin, L., & Zha, H. (2021). 将链接预测融入会话推荐中的多关系物品图建模。_IEEE知识与数据工程汇刊_。](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9536374\u002F) | TKDE | 2021 | 无 |\n| GNMR | [Xia, L., Huang, C., Xu, Y., Dai, P., Lu, M., & Bo, L. (2021年4月). 基于跨交互协同关系建模的多行为增强推荐。载于《2021年IEEE第37届国际数据工程会议（ICDE）》（第1931–1936页）。IEEE。](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9458929) | ICDE | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FGNMR) |\n| MB-GMN | [Xia, L., Xu, Y., Huang, C., Dai, P., & Bo, L. (2021年7月). 用于多行为推荐的图元网络。载于《第44届国际ACM SIGIR信息检索研究与发展会议论文集》（第757–766页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3404835.3462972) | SIGIR | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FMB-GMN) |\n| KHGT | [Xia, L., Huang, C., Xu, Y., Dai, P., Zhang, X., Yang, H., ... & Bo, L. (2021年5月). 面向多行为推荐的知识增强分层图变换器网络。载于《AAAI人工智能会议论文集》（第35卷，第5期，第4486–4493页）。](https:\u002F\u002Fwww.aaai.org\u002FAAAI21Papers\u002FAAAI-3071.XiaL.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fakaxlh\u002FKHGT) |\n| GHCF | [Chen, C., Ma, W., Zhang, M., Wang, Z., He, X., Wang, C., ... & Ma, S. (2021年5月). 图异构多关系推荐。载于《AAAI人工智能会议论文集》（第35卷，第5期，第3958–3966页）。](https:\u002F\u002Fwww.aaai.org\u002FAAAI21Papers\u002FAAAI-615.ChenC.pdf) | AAAI | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fchenchongthu\u002FGHCF) |\n| DMBGN | [Xiao, F., Li, L., Xu, W., Zhao, J., Yang, X., Lang, J., & Wang, H. (2021). DMBGN：用于优惠券核销率预测的深度多行为图网络。_arXiv预印本 arXiv:2106.03356_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.03356) | KDD | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ffengtong-xiao\u002FDMBGN) |\n| HMG-CR | [Yang, H., Chen, H., Li, L., Yu, P. S., & Xu, G. (2021). 面向多行为推荐的超元路径对比学习。_arXiv预印本 arXiv:2109.02859_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2109.02859) | ICDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FHaoran-Young\u002FHMG-CR) |\n| GNNH | [Yu, B., Zhang, R., Chen, W., & Fang, J. (2021). 基于图神经网络的多行为会话推荐模型。_GeoInformatica_，1–19页。](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10707-021-00439-w) | GeoInformatica | 2021 | 无 |\n\n### 多样性\n| **名称** | **论文** | **会议\u002F期刊** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| V2HT | [Li, M., Gan, T., Liu, M., Cheng, Z., Yin, J., & Nie, L. (2019年11月). 利用图卷积网络为微视频推荐长尾标签。载于《第28届ACM国际信息与知识管理会议论文集》（第509–518页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3357384.3357912) | CIKM | 2019 | 无 |\n| BGCF | [Sun, J., Guo, W., Zhang, D., Zhang, Y., Regol, F., Hu, Y., ... & Coates, M. (2020年8月). 基于贝叶斯图卷积神经网络的精准且多样化物品推荐框架。载于《第26届ACM SIGKDD国际知识发现与数据挖掘会议论文集》（第2030–2039页）。](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FJianing-Sun-5\u002Fpublication\u002F343780326_A_Framework_for_Recommending_Accurate_and_Diverse_Items_Using_Bayesian_Graph_Convolutional_Neural_Networks\u002Flinks\u002F5f85d507299bf1b53e23724f\u002FA-Framework-for-Recommending-Accurate-and-Diverse-Items-Using-Bayesian-Graph-Convolutional-Neural-Networks.pdf) | KDD | 2020 | [Python](https:\u002F\u002Fgitee.com\u002Fmindspore\u002Fmodels\u002Ftree\u002Fmaster\u002Fofficial\u002Fgnn\u002Fbgcf) |\n| DGCN | [Zheng, Y., Gao, C., Chen, L., Jin, D., & Li, Y. (2021年4月). DGCN：基于图卷积网络的多样化推荐。载于《2021年万维网大会论文集》（第401–412页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2108.06952.pdf) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab\u002FDGCN) |\n| FH-HAT | [Xie, R., Liu, Q., Liu, S., Zhang, Z., Cui, P., Zhang, B., & Lin, L. (2021). 利用多样化偏好网络提升推荐匹配的准确性和多样性。_arXiv预印本 arXiv:2102.03787_。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.03787) | 待定 | 2021 | 无 |\n| Isufi _et al._ | [Isufi, E., Pocchiari, M., & Hanjalic, A. (2021). 通过图卷积实现推荐系统中的准确度-多样性权衡。_信息处理与管理_，第58卷第2期，第102459页。](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0306457320309511) | IPM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fesilezz\u002Faccdiv-via-graphconv) |\n\n### 可解释性\n| **名称** | **论文** | **会议** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| RippleNet | [Wang, H., Zhang, F., Wang, J., Zhao, M., Li, W., Xie, X., & Guo, M. (2018年10月). Ripplenet: 在知识图谱上传播用户偏好以用于推荐系统。载于《第27届ACM国际信息与知识管理会议论文集》（第417–426页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.03467) | CIKM | 2018 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fripplenet-propagating-user-preferences-on-the) |\n| EIUM | [Huang, X., Fang, Q., Qian, S., Sang, J., Li, Y., & Xu, C. (2019年10月). 基于知识图谱的可解释交互驱动用户建模，用于序列化推荐。载于《第27届ACM国际多媒体会议论文集》（第548–556页）。](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3343031.3350893) | MM | 2019 | 无 |\n| KPRN | [Wang, X., Wang, D., Xu, C., He, X., Cao, Y., & Chua, T. S. (2019年7月). 面向推荐的知识图谱可解释推理。载于《AAAI人工智能大会论文集》（第33卷，第01期，第5329–5336页）。](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F4470\u002F4348) | AAAI | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fexplainable-reasoning-over-knowledge-graphs) |\n| RuleRec | [Ma, W., Zhang, M., Cao, Y., Jin, W., Wang, C., Liu, Y., ... & Ren, X. (2019年5月). 联合学习基于知识图谱的可解释推荐规则。载于《万维网大会论文集》（第1210–1221页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.03714) | WWW | 2019 | [Python](https:\u002F\u002Fgithub.com\u002FTHUIR\u002FRuleRec) |\n| PGPR | [Xian, Y., Fu, Z., Muthukrishnan, S., De Melo, G., & Zhang, Y. (2019年7月). 面向可解释推荐的强化学习知识图谱推理。载于《第42届国际ACM SIGIR信息检索研究与发展会议论文集》（第285–294页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.05237) | SIGIR | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Forcax\u002FPGPR) |\n| KGAT | [Wang, X., He, X., Cao, Y., Liu, M., & Chua, T. S. (2019年7月). Kgat：面向推荐的知识图谱注意力网络。载于《第25届ACM SIGKDD国际知识发现与数据挖掘会议论文集》（第950–958页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.07854) | KDD | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Fkgat-knowledge-graph-attention-network-for) |\n| TMER | [Chen, H., Li, Y., Sun, X., Xu, G., & Yin, H. (2021年3月). 基于时间元路径的可解释推荐。载于《第14届ACM国际网络搜索与数据挖掘会议论文集》（第1056–1064页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2101.01433) | WSDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FAbigale001\u002FTMER) |\n| ECFKG | [Bose, A., & Hamilton, W. (2019年5月). 图嵌入中的组合式公平约束。载于《国际机器学习会议论文集》（第715–724页）。PMLR。](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fbose19a\u002Fbose19a.pdf) | ICML | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fjoeybose\u002FFlexible-Fairness-Constraints) |\n| HAGERec | [Yang, Z., & Dong, S. (2020年). HAGERec：结合知识图谱的层次化注意力图卷积网络，用于可解释推荐。《知识系统》，第204卷，第106194页。](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0950705120304196) | KBS | 2020 | 无 |\n\n### 公平性\n| **名称** | **论文** | **会议** | **年份** | **代码** |\n| --- | --- | --- | --- | --- |\n| FairGo | [Wu, L., Chen, L., Shao, P., Hong, R., Wang, X., & Wang, M. (2021年4月). 学习推荐中的公平表示：基于图的观点。载于《2021年万维网大会论文集》（第2198–2208页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2102.09140) | WWW | 2021 | [Python](https:\u002F\u002Fgithub.com\u002Fnewlei\u002FFairGo) |\n| FairGNN | [Dai, E., & Wang, S. (2021年3月). 对歧视说不：利用有限的敏感属性信息学习公平的图神经网络。载于《第14届ACM国际网络搜索与数据挖掘会议论文集》（第680–688页）。](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.01454) | WSDM | 2021 | [Python](https:\u002F\u002Fgithub.com\u002FEnyanDai\u002FFairGNN) |\n| Fairwalk | [Rahman, T., Surma, B., Backes, M., & Zhang, Y. (2019年). Fairwalk：迈向公平的图嵌入。](https:\u002F\u002Fpublications.cispa.saarland\u002F2933\u002F1\u002FIJCAI19.pdf) | IJCAI | 2019 | [Python](https:\u002F\u002Fpaperswithcode.com\u002Fpaper\u002Ffairwalk-towards-fair-graph-embedding) |\n| CFCGE | [Bose, A., & Hamilton, W. (2019年5月). 图嵌入中的组合式公平约束。载于《国际机器学习会议论文集》（第715–724页）。PMLR。](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fbose19a\u002Fbose19a.pdf) | ICML | 2019 | [Python](https:\u002F\u002Fgithub.com\u002Fjoeybose\u002FFlexible-Fairness-Constraints) |","# GNN-Recommender-Systems 快速上手指南\n\n本指南旨在帮助开发者快速了解并复现基于图神经网络（GNN）的推荐系统算法。该项目是一个算法索引库，汇集了匹配、排序、重排序及不同场景下的主流 GNN 推荐模型。\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**：Linux (推荐 Ubuntu 18.04+) 或 macOS。Windows 用户建议使用 WSL2。\n*   **Python 版本**：3.7 - 3.9 (大多数论文代码在此范围内验证通过)。\n*   **核心依赖**：\n    *   `PyTorch` >= 1.7.0\n    *   `CUDA` (可选，但强烈建议安装以加速训练，版本需与 PyTorch 匹配)\n    *   `NumPy`, `Pandas`, `Scikit-learn`\n*   **包管理工具**：推荐使用 `conda` 或 `pip`。\n\n> **国内加速建议**：\n> 安装 Python 依赖时，建议使用清华或阿里镜像源以提升下载速度：\n> ```bash\n> pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple \u003Cpackage_name>\n> ```\n\n## 安装步骤\n\n由于本项目是多个独立算法的索引集合，而非单一的 Python 包，因此**没有统一的安装命令**。您需要根据需求选择特定模型进行克隆和配置。\n\n### 1. 克隆项目或特定模型仓库\n您可以先克隆本索引仓库查看列表，然后跳转到具体模型的代码仓库（README 表格中的 \"Code\" 列链接）。\n\n```bash\n# 克隆索引仓库（可选，用于查阅列表）\ngit clone https:\u002F\u002Fgithub.com\u002Fyour-repo\u002FGNN-Recommender-Systems.git\n\n# 示例：克隆一个具体的模型，如 LightGCN (需替换为实际仓库地址)\ngit clone https:\u002F\u002Fgithub.com\u002Fkuandeng\u002Flightgcn.git\ncd lightgcn\n```\n\n### 2. 创建虚拟环境并安装依赖\n进入具体模型目录后，通常会有 `requirements.txt` 文件。\n\n```bash\n# 创建 conda 环境\nconda create -n gnn-rec python=3.8\nconda activate gnn-rec\n\n# 安装 PyTorch (以 CUDA 11.3 为例，其他版本请访问 pytorch.org 查询)\npip install torch torchvision torchaudio --extra-index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu113\n\n# 安装该模型所需的特定依赖\npip install -r requirements.txt\n# 若无 requirements.txt，通常只需安装基础库：\n# pip install numpy pandas scikit-learn scipy\n```\n\n## 基本使用\n\n不同模型的数据预处理和运行脚本略有差异，但总体流程一致：**准备数据 -> 配置参数 -> 运行训练\u002F评估**。\n\n以下以经典的 **LightGCN** 模型为例，展示最简使用流程：\n\n### 1. 准备数据集\n大多数 GNN 推荐代码需要特定的数据格式（通常是交互矩阵或 `.txt` 列表）。项目通常会提供示例数据或下载脚本。\n\n```bash\n# 进入数据目录并下载示例数据 (具体命令视具体模型仓库而定)\ncd data\nsh download_data.sh \n# 或者手动将 Yelp\u002FAmazon\u002FGowalla 等数据集放入 data 文件夹\n```\n\n### 2. 运行训练与评估\n大多数模型提供统一的入口脚本（如 `main.py` 或 `run.sh`）。\n\n```bash\n# 返回项目根目录\ncd ..\n\n# 运行训练脚本\n# 常见参数包括：--dataset (数据集名), --epochs (轮数), --lr (学习率)\npython main.py --dataset yelp2018 --epochs 1000 --lr 0.001\n\n# 如果项目提供 shell 脚本，可直接运行\nbash run_lightgcn.sh\n```\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 Recall@K, NDCG@K），结果文件也可能保存在 `results\u002F` 或 `logs\u002F` 目录下。\n\n```text\nEpoch: 999 | Recall@20: 0.0523 | NDCG@20: 0.2841\nTraining finished. Best model saved.\n```\n\n> **提示**：若要尝试其他场景（如社交推荐 DiffNet、序列推荐 DGRec 等），请参照 README 表格中的链接进入对应仓库，其使用逻辑与上述步骤类似。","某中型电商平台的算法团队正致力于优化其商品推荐系统，试图从传统的协同过滤升级为能捕捉复杂用户 - 商品关系的图神经网络模型。\n\n### 没有 GNN-Recommender-Systems 时\n- **选型迷茫**：面对海量的 GNN 论文，团队难以快速甄别哪些算法（如 LightGCN 或 PinSage）真正适用于当前的匹配或排序阶段，调研耗时数周。\n- **场景错配**：缺乏对社交推荐、序列推荐等细分场景的系统分类，导致错误地将通用模型应用于需要处理时间序列行为的会话推荐场景，效果不佳。\n- **复现困难**：找不到经过验证的代码实现，工程师需从零复现论文逻辑，常因细节缺失导致模型无法收敛或性能远低于预期。\n- **目标单一**：仅关注准确率，忽视了多样性、公平性及可解释性等现代推荐系统必备的多目标优化需求，导致上线后用户投诉推荐结果单一。\n\n### 使用 GNN-Recommender-Systems 后\n- **精准导航**：利用其按推荐阶段（匹配、排序、重排）整理的索引，团队迅速锁定了适合大规模稀疏数据的 LightGCN 作为基线模型，将技术选型周期缩短至 2 天。\n- **场景对齐**：通过“不同推荐场景”分类，直接定位到针对序列推荐的专用算法，完美契合平台用户浏览路径长、依赖历史行为的特点。\n- **开箱即用**：借助提供的官方代码链接，团队快速搭建了可运行的基准框架，避免了重复造轮子，将精力集中在业务数据适配上。\n- **多维优化**：参考“不同推荐目标”章节，引入了兼顾多样性和公平性的算法变体，显著提升了长尾商品的曝光率，增强了用户体验。\n\nGNN-Recommender-Systems 通过提供结构化的算法索引与资源指引，将推荐系统的研发从“大海捞针”转变为“按图索骥”，极大加速了图神经网络在工业界的落地进程。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ftsinghua-fib-lab_GNN-Recommender-Systems_7197cd78.png","tsinghua-fib-lab","FIB LAB, Tsinghua University","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Ftsinghua-fib-lab_f779d872.png","",null,"liyong07@tsinghua.edu.cn","http:\u002F\u002Ffi.ee.tsinghua.edu.cn\u002F","https:\u002F\u002Fgithub.com\u002Ftsinghua-fib-lab",1075,145,"2026-04-02T08:36:19",4,"未说明",{"notes":90,"python":88,"dependencies":91},"该 README 文件是一个基于图神经网络（GNN）的推荐系统算法索引和综述列表，列出了多个不同阶段、场景和目标下的算法名称、论文链接及代码仓库地址。文件中并未包含具体的安装指南、环境配置要求或统一的运行依赖说明。每个列出的算法（如 LightGCN, Pin-Sage 等）都有独立的代码仓库，用户需要访问各个算法对应的代码链接以获取具体的运行环境需求。",[],[18],[94,95,96,97,98,99,100,101,102,103],"gnn","graph-neural-networks","gcn","graph-convolutional-networks","recommendation-system","recommendation","recommendation-algorithms","recommender-system","graph-representation-learning","information-retrieval","2026-03-27T02:49:30.150509","2026-04-06T07:23:05.978626",[],[]]