基于图注意力的神经协同过滤社会推荐算法

doi:10.11896/jsjkx.211200019

摘要/Abstract

摘要： 互联网技术的发展使得信息过载问题日趋严重,为了解决传统推荐技术的数据稀疏和冷启动问题,社会推荐逐渐成为近年来的研究热点。图神经网络(GNNs)作为一种能够自然整合节点信息和拓扑结构的网络,为改进社会推荐提供了巨大的潜力。但基于图神经网络的社会推荐还存在许多挑战,例如,如何从用户项目交互图和社交网络图中学习准确的用户和项目的潜在因子表示;简单映射用户和项目的固有属性来获取嵌入,但用户项目交互的关键协作信号未被学习。为了学习更准确的潜在因子表示,捕获关键的协作信号,提升推荐系统的性能,提出了基于图注意力的神经协同过滤社会推荐模型(AGNN-SR)。该模型基于用户项目交互图和社交网络图,通过多头注意力机制多角度地学习用户和项目的潜在因子;此外,图神经网络利用高阶连通性递归地在图上传播嵌入信息,显式编码协作信号,探索用户和项目之间的深层复杂的交互关系。最后,在3个真实数据集上验证了AGNN-SR模型的有效性。

关键词: 社会推荐, 图神经网络, 多头注意力, 神经协同过滤

Abstract: The development of Internet technology has made the problem of information overload more and more serious.In order to solve the problems of data sparse and cold start of traditional recommendation technology,social recommendation has gradually become a research hotspot in recent years.As a network,graph neural networks(GNNs)can naturally integrate node information and topology,offer great potential for improving social recommendation.But there are still many challenges for social recommendation based on graph neural network.For example,how to learn accurate latent factor representations of users and items from user-item interaction graphs and social network graphs;Simply mapping of inherent properties of users and items to obtain embeddings,but key collaborative signals of user-item interactions are not learned.In order to learn more accurate latent factor representations,capture key collaborative signals,and improve the performance of recommender systems,a graph attention-based neural collaborative filtering social recommendation model(AGNN-SR) is proposed.The model is based on user-item interaction graphs and social network graphs,and learns latent factors of users and items from multiple perspectives through a multi-head attention mechanism.In addition,graph neural networks utilize higher-order connectivity to recursively propagate embedding information on the graph,explicitly encoding collaborative signaling to explore deep and complex interactions between users and items.Finally,the effectiveness of the AGNN-SR model is verified on three real datasets.

Key words: Social recommendation, Graph neural network, Multi-head attention, Neural collaborative filtering

中图分类号:

TP301

章琪, 于双元, 尹鸿峰, 徐保民. 基于图注意力的神经协同过滤社会推荐算法[J]. 计算机科学, 2023, 50(2): 115-122. https://doi.org/10.11896/jsjkx.211200019

ZHANG Qi, YU Shuangyuan, YIN Hongfeng, XU Baomin. Neural Collaborative Filtering for Social Recommendation Algorithm Based on Graph Attention[J]. Computer Science, 2023, 50(2): 115-122. https://doi.org/10.11896/jsjkx.211200019

参考文献

[1]ZHAO J Y,ZHUANG F Z,AO X,et al.A Overview of Collaborative Filtering Recommendation System[J].Journal of Cyber Security,2021,6(5):17-34.
[2]ZHAO W T,ZHANG S.Collaborative Filtering AlgorithmBased on User Preference Under Sparse Data[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2021,33(4):669-674.
[3]KANG Y,LI T,LI H,et al.Recommendation Model Fusingwith Knowledge Graph and Collaborative Filtering[J].Compu-ter Engineering,2020,46(12):73-79,87.
[4]SHEN J,QIAO S J,HAN N,et al.Personalized Recommendation Model with Multi Information[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2021,35(3):128-138.
[5]SHI H Y,NI Y D.Research Progress on Cold Start of Recommendation System[J].Research on Library Science,2021(12):2-10.
[6]MA H,YANG H,LYU M R,et al.Sorec:Social RecommendationUsing Probabilistic Matrix Factorization[C]//Proceedings of the 17th ACM Conference on Information and Knowledge Management.Association for Computing Machinery.2008:931-940.
[7]MA H,ZHOU D,LIU C,et al.Recommender Systems with Social Regularization[C]//Proceedings of the Forth International Conference on Web Search and Web Data Mining(WSDM 2011).Association for Computing Machinery,2011:287-296.
[8]JAMALI M,ESTER M.A Matrix Factorization Technique with Trust Propagation for Recommendation in Social Networks[C]//Proceedings of the Fourth ACM Conference on Recommender Systems.Association for Computing Machinery,2010:135-142.
[9]GUO G,ZHANG J,YORKE-SMITH N.TrustSVD:Collaborative Filtering with Both the Explicit and Implicit Influence of User Trust and of Item Ratings[C]//Twenty-Ninth AAAI Conference on Artificial Intelligence.2015.
[10]YANG B,LEI Y,LIU J,et al.Social collaborative filtering by trust[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(8):1633-1647.
[11]WU L,SUN P,HONG R,et al.SocialGCN:An efficient graph convolutional network based model for social recommendation[J].arXiv:1811.02815,2018.
[12]FAN W,MA Y,LI Q,et al.Graph Neural Networks for Social Recommendation[C]//The World Wide Web Conference.ACM,2019:417-426.
[13]GUO Z,WANG H.A deep graph neural network-based mechanism for social recommendations[J].IEEE Transactions on Industrial Informatics,2020,17(4):2776-2783.
[14]LUO D,BIAN Y,ZHANG X,et al.Attentive social recommendation:towardsuser and item diversities[J].arXiv:2011.04797,2020.
[15]SONG C,WANG B,JIANG Q,et al.Social Recommendationwith Implicit Social Influence [C]//Proceedings of the 44th International ACMSIGIR Conference on Research and Development in Information Retrieval.Association for Computing Machinery,2021:1788-1792.
[16]YU J,YIN H,LI J,et al.Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation[C]//Proceedings of the Web Conference 2021.Association for Computing Machinery,2021:413-424.
[17]LIU Y,CHEN L,HE X,et al.Modelling high-order social relations for item recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(9):4385-4397.
[18]HUANG C,XU H,XU Y,et al.Knowledge-Aware CoupledGraph Neural Network for Social Recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.AAAI,2021:4115-4122.
[19]ZHANG J,GAO C,JIN D P,et al.Group-buying recommendation for social e-commerce[J].arXiv:2010.06848,2020.
[20]BAI T,ZHANG Y,WU B,et al.Temporal Graph Neural Networks for Social Recommendation[C]// Proceedings of the 2020 IEEE International Conference on Big Data(Big Data).IEEE,2020:898-903.
[21]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[22]MCPHERSON M,SMITH-LOVIN L,COOK J M.Birds of afeather:homophily in social networks[J/OL].Annual Review of Sociology,2001,27:415-444.http://www.jstor.org/stable/2678628.
[23]MARSDEN P V,FRIEDKIN N E.Network studies of social influence[J].Sociological Methods & Research,1993,22(1):127-151.
[24]TANG J,HU X,LIU H.Social recommendation:a review[J].Social Network Analysis&Mining,2013,3(4):1113-1133.
[25]YANG X,GUO Y,LIU Y,et al.A survey ofcollaborative filtering based social recommender systems[J].Computer Communications,2014,41(5):1-10.
[26]GOLBECK J A.Computing and applying trust in web-based social networks[D].Maryland,USA:University of Maryland,College Park,2005.
[27]GOLBECK J,MANNES A.Using Trust and Provenance forContent Filtering on the Semantic Web[C]//Proceedings of the Workshop on Models of Trust for the Web.Edinburgh,UK,2006:23-35.
[28]MASSA P,AVESANI P.Trust-aware collaborative filtering for recommender systems[C]//OTM Confederated International Conferences on the Move to Meaningful Internet Systems.Berlin:Springer,2004:492-508.
[29]JIANG M,CUI P,LIU R,et al.Social Contextual Recommendation[C]//Proceedings of the 21st ACM International Confe-rence on Information and Knowledge Management.Association for Computing Machinery.2012:45-54.
[30]HAMILTON W L,YING R,LESKOVEC J.Inductive Representation Learning on Large Graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.Curran Associates Inc,2017:1025-1035.
[31]VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[C]//Advances in Neural Information Processing Systems.2017:5998-6008.
[32]BERG R,KIPF T N,WELLING M.Graph convolutional matrix completion[J].arXiv:1706.02263,2017.
[33]MAAS A L,HANNUN A Y,NG A Y.Rectifier Nonlinearities Improve Neural Network Acoustic Models[C]//Proceedings of the ICML Workshop on Deep Learning for Audio,Speech and Language Processing.2013.
[34]SALAKHUTDINOV R,MNIH A.Probabilistic Matrix Factorization[C]//Proceedings of the 20th International Conference on Neural Information Processing Systems.Curran Associates Inc,2007:1257-1264.
[35]HE X,LIAO L,ZHANG H,et al.Neural Collaborative Filtering[C]//Proceedings of the 26th International Conference on World Wide Web.International World Wide Web Conferences Steering Committee.2017:173-182.
[36]MARSDEN P V,FRIEDKIN N E.Network studies of social influence[J].Sociological Methods & Research,1993,22(1):127-151.
[37]WANG X,HE X,WANG M,et al.Neural Graph Collaborative Filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019.

相关文章 15

[1]	陈富强, 寇嘉敏, 苏利敏, 李克. 基于图神经网络的多信息优化实体对齐模型 Multi-information Optimized Entity Alignment Model Based on Graph Neural Network 计算机科学, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242
[2]	于健, 赵满坤, 高洁, 王聪源, 李亚蓉, 张文彬. 基于高阶和时序特征的图神经网络社会化推荐算法研究 Study on Graph Neural Networks Social Recommendation Based on High-order and Temporal Features 计算机科学, 2023, 50(3): 49-64. https://doi.org/10.11896/jsjkx.220700108
[3]	郝敬宇, 文静轩, 刘华锋, 景丽萍, 于剑. 结合全局信息的深度图解耦协同过滤 Deep Disentangled Collaborative Filtering with Graph Global Information 计算机科学, 2023, 50(1): 41-51. https://doi.org/10.11896/jsjkx.220900255
[4]	顾希之, 邵蓥侠. 基于影响力剪枝的图神经网络快速计算图精简 Fast Computation Graph Simplification via Influence-based Pruning for Graph Neural Network 计算机科学, 2023, 50(1): 52-58. https://doi.org/10.11896/jsjkx.220900032
[5]	蒲金垚, 卜令梅, 卢永美, 叶子铭, 陈黎, 于中华. 利用异构图神经网络实现情绪-原因对的有效抽取 Utilizing Heterogeneous Graph Neural Network to Extract Emotion-Cause Pairs Effectively 计算机科学, 2023, 50(1): 205-212. https://doi.org/10.11896/jsjkx.211100265
[6]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[7]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[8]	齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126
[9]	杨炳新, 郭艳蓉, 郝世杰, 洪日昌. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用 Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition 计算机科学, 2022, 49(7): 57-63. https://doi.org/10.11896/jsjkx.210800070
[10]	熊中敏, 舒贵文, 郭怀宇. 融合用户偏好的图神经网络推荐模型 Graph Neural Network Recommendation Model Integrating User Preferences 计算机科学, 2022, 49(6): 165-171. https://doi.org/10.11896/jsjkx.210400276
[11]	邓朝阳, 仲国强, 王栋. 基于注意力门控图神经网络的文本分类 Text Classification Based on Attention Gated Graph Neural Network 计算机科学, 2022, 49(6): 326-334. https://doi.org/10.11896/jsjkx.210400218
[12]	余皑欣, 冯秀芳, 孙静宇. 结合物品相似性的社交信任推荐算法 Social Trust Recommendation Algorithm Combining Item Similarity 计算机科学, 2022, 49(5): 144-151. https://doi.org/10.11896/jsjkx.210300217
[13]	李勇, 吴京鹏, 张钟颖, 张强. 融合快速注意力机制的节点无特征网络链路预测算法 Link Prediction for Node Featureless Networks Based on Faster Attention Mechanism 计算机科学, 2022, 49(4): 43-48. https://doi.org/10.11896/jsjkx.210800276
[14]	曹合心, 赵亮, 李雪峰. 图神经网络在Text-to-SQL解析中的技术研究 Technical Research of Graph Neural Network for Text-to-SQL Parsing 计算机科学, 2022, 49(4): 110-115. https://doi.org/10.11896/jsjkx.210200173
[15]	苗旭鹏, 周跃, 邵蓥侠, 崔斌. GSO:基于图神经网络的深度学习计算图子图替换优化框架 GSO:A GNN-based Deep Learning Computation Graph Substitutions Optimization Framework 计算机科学, 2022, 49(3): 86-91. https://doi.org/10.11896/jsjkx.210700199

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed