Neighborhood Extension Mechanism Enhanced Graph Parallel Focused Attention Networks for Social Recommender System
LI Weiyue1,2, ZHU Zhiguo1,2, DONG Hao1,2, GAO Ming1,2, ZHANG Jun1,2, LIU Zilong1,2
1. School of Management Science and Engineering, Dongbei Uni-versity of Finance and Economics, Dalian 116025; 2. Key Laboratory of Big Data Management Optimization and Decision of Liaoning Province, Dongbei University of Finance and Economics, Dalian 116025
Abstract Social recommender systems are designed to predict the ratings of users for unexplored items based on their historical ratings and social connections. Most existing social recommender systems are based on graph neural networks. However, the inefficiency of attention mechanisms and the over-smoothing problem limit the precision and interpretability of rating predictions. Therefore, a neighborhood extension mechanism enhanced graph parallel focused attention network is proposed to address these issues. The overall preferences of users are decomposed into nuanced facets and a focused attention mechanism is introduced as message passing algorithm to pinpoint the item most aligned with the preferences of users based on their interaction history. Meanwhile, the mechanism identifies trustworthy friends from the social network based on diverse preferences. Furthermore, a neighborhood extension mechanism is proposed, which establishes quick link to facilitate the direct message passing between central and higher-order nodes, effectively enhancing the ability of graph focused attention network to capture the social information in higher-order ego network. Experimental results on three public benchmark datasets demonstrate the superiority of the proposed system in accurate rating prediction. Moreover, a series of visual case studies illustrate the interpretability of the system. The code for this paper can be found at: https://github.com/usernameAI/NEGA.
Fund:National Natural Science Foundation of China(No.72172025,72101051,72293563), Humanities and Social Sciences Foundation of the Ministry of Education of China(No.21YJAZH130), Natural Science Foundation of Liaoning Pro-vince(No.2024/175), Scientific Research Foundation of the Education Department of Liaoning Province(No.LJKMZ20221606,JYTZD2023050), Dalian Scientific and Technological Ta-lents Innovation Support Plan(No.2022RG17)
Corresponding Authors:
ZHU Zhiguo, Ph.D., professor. His research interests include data mining and business intelligence.
About author:: LI Weiyue, Ph.D. candidate. His research interests include recommender systems. DONG Hao, Ph.D. candidate. His research interests include large language model and system simulation. GAO Ming, Ph.D., professor. His research interests include cloud computing, big data and artificial intelligence. ZHANG Jun, Master student. His research interests include business intelligence. LIU Zilong, Ph.D., professor. His research interests include information systems.
[1] SHOKEEN J, RANA C. Social Recommender Systems: Techni-ques, Domains, Metrics, Datasets and Future Scope. Journal of Intelligent Information Systems, 2020, 54(3): 633-667. [2] ZHAO W Z, MA H F, LI Z Z, et al. Improving Social and Behavior Recommendations via Network Embedding. Information Sciences, 2020, 516: 125-141. [3] KIM A J, KO E. Do Social Media Marketing Activities Enhance Customer Equity? An Empirical Study of Luxury Fashion Brand. Journal of Business Research, 2012, 65(10): 1480-1486. [4] GOPINATH S, THOMAS J S, KRISHNAMURTHI L. Investigating the Relationship Between the Content of Online Word of Mouth, Advertising, And Brand Performance. Marketing Science, 2014, 33(2): 241-258. [5] DWIVEDI-YU J, WANG Y C, QIN L J, et al. Affective Signals in a Social Media Recommender System // Proc of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2022: 2831-2841. [6] TOMMASEL A, MENCZER F. Do Recommender Systems Make Social Media More Susceptible to Misinformation Spreaders? // Proc of the 16th ACM Conference on Recommender Systems. New York, USA: ACM, 2022: 550-555. [7] LI Q, WANG X M, WANG Z C, et al. Be Causal: De-biasing Social Network Confounding in Recommendation. ACM Transactions on Knowledge Discovery from Data, 2023, 17(1). DOI: 10.1145/3533725. [8] DU J, YE Z S, YAO L N, et al. Socially-Aware Dual Contrastive Learning for Cold-Start Recommendation // Proc of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2022: 1927-1932. [9] YANG D Z, MA J H, FENG S S, et al. IDVT: Interest-Aware Denoising and View-Guided Tuning for Social Recommendation[C/OL].[2024-02-23]. https://arxiv.org/abs/2308.15926v1. [10] QUAN Y H, DING J T, GAO C, et al. Robust Preference-Guided Denoising for Graph Based Social Recommendation // Proc of the ACM Web Conference. New York, USA: ACM, 2023: 1097-1108. [11] CAI R C, WU F Z, LI Z J, et al. REST: Debiased Social Recommendation via Reconstructing Exposure Strategies. ACM Transactions on Knowledge Discovery from Data, 2023, 18(2). DOI: 10.1145/3624986. [12] PRAKASH T, JALAN R, SINGH B, et al. CR-SoRec: BERT Driven Consistency Regularization for Social Recommendation // Proc of the 17th ACM Conference on Recommender Systems. New York, USA: ACM, 2023: 883-889. [13] WANG T L, XIA L H, HUANG C. Denoised Self-Augmented Lear-ning for Social Recommendation[C/OL]. [2024-02-23]. https://arxiv.org/pdf/2305.12685 [14] YANG Y H, WU L, ZHANG K, et al. Hyperbolic Graph Learning for Social Recommendation. IEEE Transactions on Knowledge and Data Engineering, 2023. DOI: 10.1109/TKDE.2023.3343402. [15] TANG J L, HU X, LIU H. Social Recommendation: A Review. Social Network Analysis and Mining, 2013, 3(4): 1113-1133. [16] MA H. An Experimental Study on Implicit Social Recommendation // Proc of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2013: 73-82. [17] TAHERI S M, MAHYAR H, FIROUZI M, et al. Extracting Implicit Social Relation for Social Recommendation Techniques in User Rating Prediction // Proc of the 26th International Conference on World Wide Web Companion. New York, USA: ACM, 2017: 1343-1351. [18] LI Q M, HAN Z C, WU X M. Deeper Insights into Graph Convolutional Networks for Semi-supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 3538-3545. [19] MA H, YANG H X, LYU M R, et al. SoRec: Social Recommendation Using Probabilistic Matrix Factorization // Proc of the 17th ACM Conference on Information and Knowledge Management. New York, USA: ACM, 2008: 931-940. [20] MA H, KING I, LYU M R. Learning to Recommend with Social Trust Ensemble // Proc of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2009: 203-210. [21] JAMALI M, ESTER M. A Matrix Factorization Technique with Trust Propagation for Recommendation in Social Networks // Proc of the 4th ACM Conference on Recommender Systems. New York, USA: ACM, 2010: 135-142. [22] ZHANG C X, YU L, WANG Y, et al. Collaborative User Network Embedding for Social Recommender Systems // Proc of the SIAM International Conference on Data Mining. Philadelphia, USA: SIAM, 2017: 381-389. [23] FAN W Q, MA Y, LI Q, et al. Graph Neural Networks for Social Recommendation // Proc of the World Wide Web Conference. New York, USA: ACM, 2019: 417-426. [24] CHEN L Y, ZHANG H L, WU J. Integrating Dual User Network Embedding with Matrix Factorization for Social Recommender Systems // Proc of the International Joint Conference on Neural Networks. Washington, USA: IEEE, 2019. DOI: 10.1109/IJCNN.2019.8851715. [25] WANG C Y, LI L X, ZHANG H Y, et al. Quaternion-Based Knowledge Graph Neural Network for Social Recommendation. Knowledge-Based Systems, 2022, 257. DOI: 10.1016/J.knosys.2022.109940. [26] YANG L W, LIU Z W, DOU Y T, et al. ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation // Proc of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2021: 2141-2145. [27] SALAMAT A, LUO X, JAFARI A. HeteroGraphRec: A Heterogeneous Graph-Based Neural Networks for Social Recommendations. Knowledge-Based Systems, 2021, 217. DOI: 10.1016/j.knosys.2021.106817. [28] CHEN J J, XIN X, LIANG X F, et al. GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(5): 4813-4824. [29] QIAO P P, ZHANG Z W, LI Z T, et al. TAG: Joint Triple-Hie-rarchical Attention and GCN for Review-Based Social Recommender System. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(10): 9904-9919. [30] SINHA R, SWEARINGEN K. The Role of Transparency in Re-commender Systems // Proc of the Extended Abstracts on Human Factors in Computing Systems. New York, USA: ACM, 2002: 830-831. [31] TINTAREV N. Explanations of Recommendations // Proc of the ACM Conference on Recommender Systems. New York, USA: ACM, 2007: 203-206. [32] FESTINGER L. A Theory of Social Comparison Processes. Human Relations, 1954, 7(2): 117-140. [33] LAAKASUO M, ROTKIRCH A, BERG V, et al. The Company You Keep: Personality and Friendship Characteristics. Social Psychological and Personality Science, 2017, 8(1): 66-73. [34] CRANDALL D, COSLEY D, HUTTENLOCHER D, et al. Feedback Effects Between Similarity and Social Influence in Online Communities // Proc of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2008: 160-168. [35] XU G D, WU Z, ZHANG Y C, et al. Social Networking Meets Recommender Systems: Survey. International Journal of Social Network Mining, 2015, 2(1): 64-100. [36] ZHAO T, MCAULEY J, KING I. Leveraging Social Connections to Improve Personalized Ranking for Collaborative Filtering // Proc of the 23rd ACM International Conference on Information and Know-ledge Management. New York, USA: ACM, 2014: 261-270. [37] YANG B, LEI Y, LIU J M, et al. Social Collaborative Filtering by Trust. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(8): 1633-1647. [38] GUO G B, ZHANG J, YORKE-SMITH N. TrustSVD: Collaborative Filtering with Both the Explicit and Implicit Influence of User Trust and of Item Ratings. Proceedings of the AAAI Conference on Artificial Intelligence, 2015, 29(1): 123-129. [39] MA H, ZHOU D Y, LIU C, et al. Recommender Systems with Social Regularization // Proc of the 4th ACM International Confe-rence on Web Search and Data Mining. New York, USA: ACM, 2011: 287-296. [40] TANG J L, WANG S H, HU X, et al. Recommendation with Social Dimensions. Proceedings of the AAAI Conference on Artificial Intelligence, 2016, 30(1): 251-257. [41] JIANG M, CUI P, WANG F, et al. Scalable Recommendation with Social Contextual Information. IEEE Transactions on Know-ledge and Data Engineering, 2014, 26(11): 2789-2802. [42] RUSCH T K, BRONSTEIN M M, MISHRA S. A Survey on Over-smoothing in Graph Neural Networks[C/OL]. [2024-02-23]. https://arxiv.org/pdf/2303.10993. [43] KERIVEN N. Not Too Little, Not Too Much: A Theoretical Analysis of Graph(Over) Smoothing // Proc of the 36th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2022: 2268-2281. [44] ZHAO L X, AKOGLU L. PAIRNORM: Tackling Oversmoothing in GNNs[C/OL]. [2024-02-23]. https://arxiv.org/pdf/1909.12223. [45] LI G H, MULLER M, THABET A, et al. DeepGCNs: Can GCNs Go as Deep as CNNs? // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 9266-9275. [46] RUSCH T K, CHAMBERLAIN B, ROWBOTTOM J, et al. Graph-Coupled Oscillator Networks. Journal of Machine Learning Research, 2022, 162: 18888-18909. [47] PETERS B, NICULAE V, MARTINS A F T. Sparse Sequence-to-Sequence Models. // Proc of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2019: 1504-1519. [48] MARTINS A, ASTUDILLO R. From Softmax to Sparsemax: A Sparse Model of Attention and Multi-label Classification. Journal of Machine Learning Research, 2016, 48: 1614-1623. [49] TSALLIS C. Possible Generalization of Boltzmann-Gibbs Statistics. Journal of Statistical Physics, 1988, 52(1/2): 479-487. [50] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778. [51] YUAN J H, SONG Z H, SUN M Y, et al. Dual Sparse Attention Network for Session-Based Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(5): 4635-4643. [52] HE X N, DENG K, WANG X, et al. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation // Proc of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2020: 639-648. [53] GUO G B, ZHANG J, YORKE-SMITH N. A Novel Evidence-Based Bayesian Similarity Measure for Recommender Systems. ACM Transactions on the Web, 2016, 10(2). DOI: 10.1145/2856037. [54] GUO G B, ZHANG J, THALMANN D, et al. ETAF: An Exten-ded Trust Antecedents Framework for Trust Prediction // Proc of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. Washington, USA: IEEE, 2014: 540-547. [55] SHI C, HU B B, ZHAO W X, et al. Heterogeneous Information Network Embedding for Recommendation. IEEE Transactions on Knowledge and Data Engineering, 2018, 31(2): 357-370. [56] LOSHCHILOV I, HUTTER F. Decoupled Weight Decay Regularization[C/OL]. [2024-02-23]. https://arxiv.org/pdf/1711.05101. [57] KOREN Y, BELL R, VOLINSKY C. Matrix Factorization Techniques for Recommender Systems. Computer, 2009, 42(8): 30-37. [58] SALAKHUTDINOV R, MNIH A. Probabilistic Matrix Factorization // Proc of the 20th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2007: 1257-1264. [59] KOREN Y. Factorization Meets the Neighborhood: A Multifaceted Collaborative Filtering Model // Proc of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2008: 426-434. [60] WANG L, XU M, ZHANG Q G, et al. Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation[C/OL].[2024-02-23]. https://arxiv.org/pdf/2403.03578. [61] WATTS D J, STROGATZ S H. Collective Dynamics of 'Small-World' Networks. Nature, 1998, 393(6684): 440-442. [62] YUAN Q, CHEN L, ZHAO S W. Factorization vs. Regularization: Fusing Heterogeneous Social Relationships in Top-N Recommendation // Proc of the 5th ACM Conference on Recommender Systems. New York, USA: ACM, 2011: 245-252. [63] MCPHERSON M, SMITH-LOVIN L, COOK J M. Birds of a Feather: Homophily in Social Networks. Annual Review of Sociology, 2001, 27(1): 415-444. [64] MA L Y, KRISHNAN R, MONTGOMERY A L. Latent Homophily or Social Influence? An Empirical Analysis of Purchase within a Social Network. Management Science, 2015, 61(2): 454-473. [65] ANAGNOSTOPOULOS A, KUMAR R, MAHDIAN M. Influence and Correlation in Social Networks // Proc of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2008: 7-15. [66] SOHN J W, KIM J K. Factors That Influence Purchase Intentions in Social Commerce. Technology in Society, 2020, 63. DOI: 10.1016/j.techsoc.2020.101365 [67] MCCLURE C, SEOCK Y K. The Role of Involvement: Investigating the Effect of Brand's Social Media Pages on Consumer Purchase Intention. Journal of Retailing and Consumer Services, 2020, 53. DOI: 10.1016/j.jretconser.2019.101975 [68] BLEIZE D N M, ANTHEUNIS M L. Factors Influencing Purchase Intent in Virtual Worlds: A Review of the Literature. Journal of Marketing Communications, 2019, 25(4): 403-420. [69] LIU X, YU T, XIE K G, et al. Interact with the Explanations: Causal Debiased Explainable Recommendation System // Proc of the 17th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2024: 472-481. [70] ZHANG Y F, LAI G K, ZHANG M, et al. Explicit Factor Models for Explainable Recommendation Based on Phrase-Level Sentiment Analysis // Proc of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2014: 83-92. [71] LIN Y J, REN P J, CHEN Z M, et al. Explainable Outfit Reco-mmendation with Joint Outfit Matching and Comment Generation. IEEE Transactions on Knowledge and Data Engineering, 2019, 32(8): 1502-1516. [72] TSAI C H, BRUSILOVSKY P. The Effects of Controllability and Explainability in a Social Recommender System. User Modeling and User-Adapted Interaction, 2021, 31: 591-627. [73] SHARMA A, COSLEY D. Do Social Explanations Work? Studying and Modeling the Effects of Social Explanations in Recommender Systems // Proc of the 22nd International Conference on World Wide Web. New York, USA: ACM, 2013: 1133-1144. [74] GE Y Q, LIU S C, FU Z H, et al. A Survey on Trustworthy Re-commender Systems. ACM Transactions on Recommender Systems, 2024. DOI: 10.1145/3652891. [75] BONHARD P, SASSE M A. 'Knowing Me, Knowing You'-Using Profiles and Social Networking to Improve Recommender Systems. BT Technology Journal, 2006, 24(3): 84-98. [76] XIA L H, SHAO Y Z, HUANG C, et al. Disentangled Graph Social Recommendation // Proc of the IEEE 39th International Conference on Data Engineering. Washington, USA: IEEE, 2023: 2332-2344. [77] LI N, GAO C, JIN D P, et al. Disentangled Modeling of Social Homophily and Influence for Social Recommendation. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(6): 5738-5751. [78] SHA X, SUN Z, ZHANG J. Disentangling Multi-facet Social Relations for Recommendation. IEEE Transactions on Computational Social Systems, 2022, 9(3): 867-878. [79] ZHENG L, LIU Q, ZHANG Y M. Social Recommendation Based on Preference Disentangle Aggregation // Proc of the 7th International Conference on Big Data and Information Analytics. Washington, USA: IEEE, 2021: 1-8. [80] LIU J W, YANG C, LU Z Y, et al. Towards Graph Foundation Models: A Survey and Beyond[C/OL].[2024-02-23]. https://arxiv.org/pdf/2310.11829. [81] LI Y H, LI Z X, WANG P S, et al. A Survey of Graph Meets Large Language Model: Progress and Future Directions[C/OL].[2024-02-23]. https://arxiv.org/pdf/2311.12399.
2024, Vol. 37 
