基於社交理論，具有社交關係的用戶間會互相影響對方的購物偏好及 行為，因此為了探索社交資訊於推薦任務的運用並且緩解推薦任務中的冷啟動問題，近年來社交推薦的相關研究逐漸受到重視。然而，在現存的社 交推研究中仍有部分問題尚未被探討，像是大多數現存的推薦系統模型僅 針對非重疊型社群架構進行研究，因此忽略了重疊型社群架構中更豐富的社交資訊。此外，來自社群中的社交影響力也尚未被探討。因此，為了探 索更豐富的社交及社群資訊，我們提出了重疊型社群感知社交推薦模型。 其中，我們分別針對社交網路及社群網路設計了圖注意力網路模組，進而模擬在社交網路及社群網路中的影響力傳播，並且為了整合受不同領域影 響的用戶偏好而提出了基於注意力機制的網路層，進而學習更精準的用戶偏好。最終，為了驗證提出模型的有效性，我們使用了三種社交推薦研究常見的資料集進行實驗。我們的實驗結果呈現了我們提出的方法在推薦系統中預測評分的任務達到良好的效果。

Social influence affects user preference and behavior based on social theory. Therefore, social recommendation has been researched for exploring the information from the social network in the recommendation task and alleviating the cold-start problem. However, there are several challenges that have not yet been well addressed. The existing social recommendation models focus on leveraging non-overlapping community structure which ignores informative features from the overlapping community structure. Furthermore, the influence from communities has not been well exploited in the recent social recommendation research. To explore informative social networks and community information, we propose a novel overlapping community-aware social recommendation. To exploit the influence from social network and community networks, we design graph attention network modules to simulate the influence propagation among social and community networks, respectively. In addition, we propose an attention-based network to capture the precise user preference for aggregating the influence preference from diverse domains. Comprehensive experiments are conducted on three benchmark datasets. We demonstrate the effectiveness of our proposed approach on rating prediction of recommendation tasks.

[1] M. McPherson, L. Smith-Lovin, and J. M. Cook, “Birds of a feather: Homophily in social networks,” Annual Review of Sociology, vol. 27, no. 1, pp. 415–444, 2001.
[2] P. V. MARSDEN and N. E. FRIEDKIN, “Network studies of social influence,” Sociological Methods & Research, vol. 22, no. 1, pp. 127–151, 1993.
[3] C. Zhang, L. Yu, Y. Wang, C. Shah, and X. Zhang, Collaborative User Network Embedding for Social Recommender Systems, pp. 381–389. 06 2017.
[4] L. Yang, Z. Liu, Y. Dou, J. Ma, and P. S. Yu, “Consisrec: Enhancing gnn for social recommendation via consistent neighbor aggregation,” ACM, 2021.
[5] J. Wu, W. Fan, J. Chen, S. Liu, Q. Li, and K. Tang, “Disentangled contrastive learning for social recommendation,” in Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 4570–4574, 2022.
[6] J. Guan, X. Huang, and B. Chen, “Community-aware social recommendation: A unified scsvd framework,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 3, pp. 2379–2393, 2023.
[7] C. Chen, Z. Min, Y. Liu, and S. Ma, “Social attentional memory network: Modeling aspect- and friend-level differences in recommendation,” pp. 177–185, 01 2019.
[8] B. Fu, W. Zhang, G. Hu, X. Dai, S. Huang, and J. Chen, “Dual side deep context-aware modulation for social recommendation,” in Proceedings of the Web Conference 2021 (WWW ’21), April 19–23, 2021, Ljubljana, Slovenia, 2021.
[9] N. Li, C. Gao, D. Jin, and Q. Liao, “Disentangled modeling of social homophily and influence for social recommendation,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 6, pp. 5738–5751, 2023.
[10] C. Huang, H. Xu, Y. Xu, P. Dai, L. Xia, M. Lu, L. Bo, H. Xing, X. Lai, and Y. Ye, “Knowledge-aware coupled graph neural network for social recommendation,” ArXiv, vol. abs/2110.03987, 2021.
[11] H. Ma, I. King, and M. Lyu, “Learning to recommend with social trust ensemble,” pp. 203–210, 07 2009.
[12] J. Tang, S. Wang, X. Hu, D. Yin, Y. Bi, Y. Chang, and H. Liu, “Recommendation with social dimensions,” in AAAI Conference on Artificial Intelligence, 2016.
[13] M. Jamali and M. Ester, “A matrix factorization technique with trust propagation for recommendation in social networks,” in ACM Conference on Recommender Systems, 2010.
[14] Y. Lu, R. Xie, C. Shi, Y. Fang, W. Zhang, X. Zhang, and L. Lin, “Social influence attentive neural network for friend-enhanced recommendation,” in Proceedings of ECML-PKDD, 2020.
[15] J. Yu, H. Yin, J. Li, Q. Wang, N. Q. V. Hung, and X. Zhang, “Self-supervised multi-channel hypergraph convolutional network for social recommendation,” in Proceedings of the web conference 2021, pp. 413–424, 2021.
[16] L. Wu, P. Sun, Y. Fu, R. Hong, X. Wang, and M. Wang, “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, 2019.
[17] C. Chen, M. Zhang, C. Wang, W. Ma, M. Li, Y. Liu, and S. Ma, “An efficient adaptive transfer neural network for social-aware recommendation,” in Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 225–234, 2019.
[18] Q. Wu, H. Zhang, X. Gao, P. He, P. Weng, H. Gao, and G. Chen, “Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems,” 03 2019.
[19] W. Fan, Y. Ma, Q. Li, Y. He, E. Zhao, J. Tang, and D. Yin, “Graph neural networks for social recommendation,” in The world wide web conference, pp. 417–426, 2019.
[20] H. Liu, C. Zheng, D. Li, Z. Zhang, K. Lin, X. Shen, N. N. Xiong, and J. Wang, “Multi-perspective social recommendation method with graph representation learning,” Neurocomputing, vol. 468, pp. 469–481, 2022.
[21] T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016.
[22] S. Brody, U. Alon, and E. Yahav, “How attentive are graph attention networks?,” in International Conference on Learning Representations, 2022.
[23] P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, “Graph attention networks,” 2018.
[24] A. Epasto, S. Lattanzi, and R. Leme, “Ego-splitting framework: from non-overlapping to overlapping clusters,” pp. 145–154, 08 2017.
[25] G. Guo, J. Zhang, and N. Yorke-Smith, “A novel bayesian similarity measure for recommender systems,” in Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI), pp. 2619–2625, 2013.
[26] A. Mnih and R. R. Salakhutdinov, “Probabilistic matrix factorization,” Advances in neural information processing systems, vol. 20, 2007.
[27] S. Funk, “Netflix update: Try this at home.” https://sifter.org/ simon/journal/20061211.html.
[28] J. Yang and J. Leskovec, “Overlapping community detection at scale: A nonnegative matrix factorization approach,” pp. 587–596, 02 2013.
[29] X. Wang, P. Cui, J. Wang, J. Pei, W. Zhu, and S. Yang, “Community preserving network embedding,” in Proceedings of the AAAI conference on artificial intelligence, vol. 31, 2017.
[30] F. Ye, C. Chen, and Z. Zheng, “Deep autoencoder-like nonnegative matrix factorization for community detection,” in Proceedings of the 27th ACM international conference on information and knowledge management, pp. 1393–1402, 2018.
[31] O. Shchur and S. Günnemann, “Overlapping community detection with graph neural networks,” Deep Learning on Graphs Workshop, KDD, 2019.