融合物品关系的图神经网络推荐算法

doi:10.11896/jsjkx.230100019

摘要/Abstract

摘要： 典型的社交推荐方法都受限于对用户的行为建模,如用户与用户之间的社交行为、用户与物品之间的交互行为,而忽略了用户感兴趣的多个物品之间存在的潜在相关性,导致信息丢失。在数据稀疏的推荐场景中,用户行为的稀疏性导致系统可用的信息不足,因此需要引入具有丰富内涵的物品关系作为辅助信息。文中致力于融合用户行为和辅助信息共同建模用户的偏好,以提升推荐的准确性。推荐系统中的数据大多可以表示为图结构,例如用户的社交行为、交互行为和物品关系,可以转化为用户-用户图、用户-物品图和物品-物品图。图神经网络在处理大规模图形数据方面颇有成效,建立一个包含物品关系的图神经网络推荐框架面临巨大的挑战:1)物品-物品关系是隐式的;2)用户-用户图、用户-物品图、物品-物品图,是3种不同类型的图;3)用户与用户、用户与物品、物品与物品之间的联系都具有异质性。为了解决上述问题,文中提出了一种新的基于图神经网络的社交推荐方法(PEVGraphRec),引入了一种数学上的方法显式地构建物品间的连接,该模型能够内在地结合3种不同的图,以便更好地学习用户偏好。最后,提出了注意力机制来综合地考虑不同信息的权重。在3个真实数据集上进行实验,实验结果证明了所提方法的有效性。

Abstract: Typical social recommendation methods are limited by modeling user behavior,such as social behavior between users,interaction behavior between users and items.However,the potential correlation between multiple items that users are interested in is ignored,leading to information loss.In recommendation scenarios with sparse data,the sparsity of user behavior leads to insufficient information available in the system,so it is necessary to introduce item relationships with rich connotations as auxiliary information.This papaer aims to integrate user behavior and auxiliary information to jointly model user preferences,so as to improve the accuracy of recommendations.Most of the data in the recommendation system can be expressed as a graph structure,such as user’s social behavior,user’s interactive behavior and item relationship,which can be converted into user-user graph,user-item graph and item-item graph.Graph neural networks(GNN) are effective in processing large-scale graphic data,and building a framework with item relations based-GNN for social recommendations is facing considerable challenges:1)the item-item relationship is implicit;2)user-user graph,user-item graph,and item-item graph are three different types of graphs;3)the relationship between user and user,user and item,item and item is heterogeneous.In order to solve the above problems,this paper proposes a new social recommendation method based on graph neural network,PEVGraphRec,which introduces a mathematical way to explicitly construct connections between items.Thismodel inherently combines three different graphs to better learn user preference.Finally,an attention mechanism is proposed to consider the weight of different information comprehensively.Comprehensive experiments on three real-world datasets verify the effectiveness of the proposed framework.

Key words: Social recommendation, Graph neural network, Item-Item graph, Heterogeneous, Attention mechanism

中图分类号:

TP183

廖冬, 于海征. 融合物品关系的图神经网络推荐算法[J]. 计算机科学, 2023, 50(11A): 230100019-9. https://doi.org/10.11896/jsjkx.230100019

LIAO Dong, YU Haizheng. Graph Neural Network Recommendation Algorithm Based on Item Relations[J]. Computer Science, 2023, 50(11A): 230100019-9. https://doi.org/10.11896/jsjkx.230100019

参考文献

[1]LIAO J,ZHOU W,LUO F,et al.SocialLGN:Light graph convolution network for social recommendation[J].Information Sciences,2022,589:595-607.
[2]LIU Z W,FAN Z W,WANG Y,et al.Augmenting Sequential Recommendation with Pseudo-PriorItems via Reversely Pre-training Transformer[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021.
[3]LI M N,TEI K J,FUKAZAWA Y.An Efficient Adaptive Attention Neural Network for Social Recommendation[J].IEEE Access,2020,8:63595-63606.
[4]WU L,LI J,SUN P,et al.DiffNet++:A Neural Influence and Interest Diffusion Network for Social Recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(10):4753-4766.
[5]WU L,SUN P,HONG R,et al.Collaborative neural social re-commendation[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,2021,51(1):464-476.
[6]CIALDINI R B,GOLDSTEIN N J.Social influence:Compliance and conformity[J].Annu.Rev.Psychol.2004,55(1):591-621.
[7]MCPHERSON M,SMITH-LOVIN L,COOK J M.Birds of aFeather:Homophily in Social Networks[J].Annual Review of Sociology,2001,27(1):415-444.
[8]RESNICK P,VARIAN H R.Recommender systems[J].Communications of the ACM,1997,40(3):56-58.
[9]TANG J,HU X,LIU H.Social recommendation:a review[J].Social Network Analysis and Mining,2013,3(4):1113-1133.
[10]JAMALI M,ESTER M.A matrix factorization technique withtrust propagation for recommendation in social networks[C]//Proceedings of the fourth ACM conference on Recommender systems.ACM,2010:135-142.
[11]SALAMAT,LUO X,JAFARI A.HeteroGraphRec:A heterogeneous graph-based neural networks for social recommendations[J].Knowledge-Based Systems,2021,217,106817.
[12]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[C]//International Conference onLearning Representations(ICLR).2017.
[13]DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutionalneural networks on graphs with fast localized spectral filtering[C]//30th Conference on Neural Information Proces-sing Systems(NIPS 2016).2016:3844-3852.
[14]BRUNA J,ZAREMBA W,SZLAM A,et al.Spectralnetworksand locally connected networks on graphs[J].arXiv:1312.6203,2013.
[15]ZHANG Y,QI P,MANNING C D.Graph convolutionoverpruned dependency trees improves relation extraction[J].arXiv:1809.10185,2018.
[16]ZHANG Y J,DU Y L,MENG X W.Group recommendation system and its application[J].Chinese Journal of Computers,2016,39(4):745-764.
[17]LIU X,MEI H Y,WANG J H.Research on Graph Neural Network Recommendation Method[J].Computer Engineering and Applications,2022,58(10):41-49.
[18]WANG J C,YUAN F J,CHEN J,et al.Stackrec:Efficient trai-ning of very deep sequential recommender models by iterative stacking.[C]//The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval,Canada.2021:357-366.
[19]LINDEN G,SMITH B,YORK J.Amazon.com recommenda-tions:Item-to-item collaborative filtering[J].IEEE Internet Computing,2003,7(1):76-80.
[20]DESHPANDE M,KARYPIS G.Item-based top-n recommendation algorithms[J].ACM Transactions on Information Systems(TOIS),2004,22(1):143-177.
[21]FAN W,MA Y,LI Q,et al.A Graph Neural Network Framework for Social Recommendations[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(5):2033-2047.
[22]XIANG R,NEVILLE J,ROGATI M.Modeling relationshipstrength in online social networks[C]//Proceedings of the 19th International Conference on World Wide Web.ACM,2010:981-990.
[23]CHEN M,LI Y H,ZHOU X Z.CoNet:Co-occurrence neural networks for recommendation[J].Future Generation Computer Systems,2021,124(3):308-314.
[24]FAN W,MA Y,LI Q,et al.Graph neural networks for social recommendation[C]//Proceedings of the WWW’19.San Francisco,CA,USA,2019:417-426.
[25]ZHANG Z P,GUO X L.PEV:New similarity measure applying to Item-based collaborative filtering algorithm[J].Journal of Chinese Computer Systems,2009,30(4):716-720.
[26]WU Q,ZHANG H,GAO X,et al,Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems[C]//The World Wide Web Conference(WWW ’19).2019:2091-2102.
[27]LIU Z W,ZHENG L,ZHANG J W.JSCN:Joint spectral convolutional network for cross domain recommendation[C]//2019 IEEE International Conference on Big Data(Big Data).IEEE,2019:850-859.
[28]SALAKHUTDINOV R,MNIH A.Probabilistic matrix factorization[C]//Proceedings of the 20th International Conference on Neural Information Processing Systems(NIPS’07).Red Hook,NY,USA,2007:1257-1264.
[29]MA H,YANG H X,LYU R M,et al.Sorec:Social recommendation using probabilistic matrix factorization[C]//Proceedings of the 17th ACM conference on Information and Knowledge Management(CIKM’08).New York,USA,2008:931-940.
[30]MA H,ZHOU D,LIU C,et al.Recommendersystems with social regularization[C]//Proceedings of the fourthACM international conference on Web Search and Data Mining.ACM,2011:287-296.
[31]WU L,SUN P,FU Y,et al.A Neural Influence Diffusion Model for Social Recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR 2019).ACM,Paris,France,2019:235-244.
[32]LI M,TEI K,FUKAZAWA Y.An efficient co-attention neural network for social recommendation[C]//Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence(WI ’19).Thessaloniki,Greece,2019:34-42.
[33]BERG R,KIPF T N,WELLING M.Graph convolutional matrix completion[C]//Proceedings of the KDD’18 Deep Learning Day.London,UK,2018.
[34]GROVER A,LESKOWEC J.node2vec:Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(KDD’16).San Francisco,CA,USA,2016:855-864.
[35]YANG L,LIU Z,DOU Y,et al.ConsisRec:Enhancing GNN for social recommendation via consistent neighbor aggregation[C]//The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR’21).ACM,2021.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed