Abstract
With the revival of social networks, many studies try to integrate social relations of users to improve the accuracy of rating prediction. However, most existing methods cannot accurately reflect how social relations affect user preferences. The main reason is that these methods only investigate the directly or indirectly reachable nodes in social networks, while ignoring global transitivity of influence. Actually, for a particular user, his preference will not only affect his neighbors but also some people he does not know, especially when the person is an opinion leader. In this paper, we propose a social influence model, SIGA, which integrates graph autoencoder and is used for the rating prediction task. First, we establish a new method to quantify the social influence of users from the perspective of information dissemination in social networks. Second, we employ graph autoencoder (GAE) to model the interaction between users and items from the view of message passing on bipartite graph, which can obtain high-quality representations of users and items. By building a hybrid architecture of social modeling and GAE, it is expected to be endowed with both benefits from them. In addition, our model is interpretable at both the structural level and attribute level. Extensive experimental results on four real-world datasets have shown the effectiveness and generalization of the proposed model.
Similar content being viewed by others
References
Basu C, Hirsh H, Cohen W et al (1998) Recommendation as classification: Using social and content-based information in recommendation. In: Aaai/iaai, pp 714–720
Bengio Y, Yao L, Alain G et al (2013) Generalized denoising auto-encoders as generative models. arXiv:13056663
Berg R, Kipf TN, Welling M (2017) Graph convolutional matrix completion. arXiv:170602263
Cao D, He X, Miao L et al (2018) Attentive group recommendation. In: The 41st international ACM SIGIR conference on research & development in information retrieval, pp 645–654
Chen Y L, Cheng L C, Chuang C N (2008) A group recommendation system with consideration of interactions among group members. Expert Syst Appl 34(3):2082–2090
Fan W, Ma Y, Li Q et al (2019) Graph neural networks for social recommendation. In: The world wide web conference, pp 417–426
Golbeck J, Hendler J et al (2006) Filmtrust: movie recommendations using trust in web-based social networks. In: Proceedings of the IEEE consumer communications and networking conference. Citeseer, pp 282–286
Guo G, Zhang J, Yorke-Smith N (2015) Trustsvd: collaborative filtering with both the explicit and implicit influence of user trust and of item ratings. In: Proceedings of the AAAI conference on artificial intelligence
Hartford J, Graham D, Leyton-Brown K, et al (2018) Deep models of interactions across sets. In: International conference on machine learning. PMLR, pp 1909–1918
He X, Liao L, Zhang H et al (2017) Neural collaborative filtering. In: Proceedings of the 26th international conference on world wide web, pp 173–182
He X, Deng K, Wang X et al (2020) 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
Jamali M, Ester M (2010) A matrix factorization technique with trust propagation for recommendation in social networks. In: Proceedings of the fourth ACM conference on recommender systems, pp 135–142
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:160902907
Kipf TN, Welling M (2016) Variational graph auto-encoders. arXiv:161107308
Lin F, Cohen W (2010) Advances in social networks analysis and mining (asonam). In: 2010 International conference on, pp 192–199
Ling Z, Xiao Y, Wang H, et al (2019) Extracting implicit friends from heterogeneous information network for social recommendation. In: Pacific rim international conference on artificial intelligence. Springer, pp 607–620
Liu C Y, Zhou C, Wu J et al (2018) Social recommendation with an essential preference space. In: Thirty-second AAAI conference on artificial intelligence
Liu F, Cheng Z, Zhu L, et al. (2021) Interest-aware message-passing gcn for recommendation. In: Proceedings of the web conference 2021, pp 1296-1305
Liu Y , Liang C, He X et al (2020) Modelling high-order social relations for item recommendation. IEEE Trans Knowl Data
Lü L, Zhang Y C, Yeung C H et al (2011) Leaders in social networks, the delicious case. PloS one 6(6):e21–202
Ma C, Ma L, Zhang Y et al (2020) Memory augmented graph neural networks for sequential recommendation. In: Proceedings of the AAAI conference on artificial intelligence, pp 5045–5052
Ma H, Yang H, Lyu MR et al (2008) Sorec: social recommendation using probabilistic matrix factorization. In: Proceedings of the 17th ACM conference on information and knowledge management, pp 931–940
Ma J, Zhou C, Cui P et al (2019) Learning disentangled representations for recommendation. arXiv:191014238
Massam P, Avesani P (2007) Trust-aware recommender systems. In: Proceedings of the 2007 ACM conference on recommender systems, pp 17–24
Monti F, Bronstein MM, Bresson X (2017) Geometric matrix completion with recurrent multi-graph neural networks. arXiv:170406803
Mu N, Zha D, He Y et al (2019) Graph attention networks for neural social recommendation. In: 2019 IEEE 31st international conference on tools with artificial intelligence ICTAI. IEEE, pp 1320–1327
Paatero P, Tapper U (1994) Positive matrix factorization: a non-negative factor model with optimal utilization of error estimates of data values. Environmetrics 5(2):111–126
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 701–710
Sedhain S, Menon AK, Sanner S et al (2015) Autorec: autoencoders meet collaborative filtering. In: Proceedings of the 24th international conference on world wide web, pp 111–112
Shenbin I, Alekseev A, Tutubalina E et al (2020) Recvae: A new variational autoencoder for top-n recommendations with implicit feedback. In: Proceedings of the 13th international conference on web search and data mining, pp 528–536
Wu J, Wang X, Feng F et al (2021) 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
Wu L, Sun P, Fu Y et al (2019a) 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
Wu Q, Zhang H, Gao X et al (2019b) Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems. In: The world wide web conference, pp 2091–2102
Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence
Ying R, He R, Chen K et al (2018) 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
Yu J, Yin H, Li J, et al. (2021) Self-supervised multi-channel hypergraph convolutional network for social recommendation. In: Proceedings of the web conference, pp 413–424
Zhang C, Song D, Huang C et al (2019) Heterogeneous graph neural network. In: Proceedings of the 25th ACM SIGKDD International conference on knowledge discovery & data mining, pp 793–803
Acknowledgements
This work is supported by Tianjin “Project + Team” Key Training Project under Grant No. XC202022.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, J., Xiao, Y., Zheng, W. et al. SIGA: social influence modeling integrating graph autoencoder for rating prediction. Appl Intell 53, 6432–6447 (2023). https://doi.org/10.1007/s10489-022-03748-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03748-1