Abstract
The social recommendation aims to alleviate data sparsity problems and improve recommendation performance by incorporating user social data. And the recent popularity of graph neural networks (GNNs) has further advanced the development of social recommendation. However, most previous research erroneously assumed that user-item interaction data, such as ratings, directly reflects user preferences for items. In reality, various non-preference factors can also influence user ratings, referred to as biases in this paper. For example, users may still rate popular or high-quality items highly even if they are not interested in them, or some users may tend to give lower ratings to most items even if they like the item. Furthermore, existing research also lacks a general method for capturing and leveraging biases. To this end, we propose BiasRec, a bias-aware social recommendation model. BiasRec initially constructs a bias matrix for each user and item, calculates bias scores, and removes them from the raw rating data. Subsequently, the debiased data is fed into a GNN to learn users’ genuine preferences. Last, it reasonably combines biases and preferences to make predictions. We performed experiments on three real-world datasets and attained state-of-the-art results, showcasing the efficacy of our model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, J., Xin, X., Liang, X., He, X., Liu, J.: Gdsrec: graph-based decentralized collaborative filtering for social recommendation. IEEE Trans. Knowl. Data Eng. 35(5), 4813–4824 (2023)
Chen, J., Dong, H., Wang, X., Feng, F., Wang, M., He, X.: Bias and debias in recommender system: a survey and future directions. ACM Trans. Inf. Syst. 41(3), 1–39 (2023)
Cialdini, R.B., Goldstein, N.J.: Social influence: compliance and conformity. Annu. Rev. Psychol. 55, 591–621 (2004)
Fan, W., Li, Q., Cheng, M.: Deep modeling of social relations for recommendation. In: Proceedings of the AAAI Conference on Artificial Intelligence vol. 32 (2018)
Fan, W., Ma, Y., Li, Q., He, Y., Zhao, E., Tang, J., Yin, D.: Graph neural networks for social recommendation. In: The World Wide Web Conference, pp. 417–426 (2019)
He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T.S.: Neural collaborative filtering. In: Proceedings of the 26th International Conference on World Wide Web, pp. 173–182 (2017)
Huang, J., Xie, R., Cao, Q., Shen, H., Zhang, S., Xia, F., Cheng, X.: Negative can be positive: signed graph neural networks for recommendation. Inf. Process. Manage. 60(4), 103403 (2023)
Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 426–434 (2008)
Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)
Li, Q., Wang, X., Wang, Z., Xu, G.: Be causal: de-biasing social network confounding in recommendation. ACM Trans. Knowl. Discov. Data 17(1), 1–23 (2023)
Liu, H., Zheng, C., Li, D., Zhang, Z., Lin, K., Shen, X., Xiong, N.N., Wang, J.: Multi-perspective social recommendation method with graph representation learning. Neurocomputing 468, 469–481 (2022)
Ma, H., Yang, H., Lyu, M.R., King, I.: Sorec: social recommendation using probabilistic matrix factorization. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management, pp. 931–940 (2008)
Mnih, A., Salakhutdinov, R.R.: Probabilistic matrix factorization. Adv. Neural. Inf. Process. Syst. 20, 1257–1264 (2007)
Peng, S., Sugiyama, K., Mine, T.: Svd-gcn: a simplified graph convolution paradigm for recommendation. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 1625–1634 (2022)
Seyedhoseinzadeh, K., Rahmani, H.A., Afsharchi, M., Aliannejadi, M.: Leveraging social influence based on users activity centers for point-of-interest recommendation. Inf. Process. Manage. 59(2), 102858 (2022)
Tang, J., Wang, K.: Personalized top-n sequential recommendation via convolutional sequence embedding. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 565–573 (2018)
Tu, K., Wu, Z., Hu, B., Zhang, Z., Cui, P., Li, X., Zhou, J.: A scalable social recommendation framework with decoupled graph neural network. In: International Conference on Database Systems for Advanced Applications, pp. 519–531. Springer (2023)
Wang, J., Li, H., Mo, T., Li, W.: A scalable social recommendation framework with decoupled graph neural network. In: International Conference on Database Systems for Advanced Applications, pp. 357–372. Springer (2023). https://doi.org/10.1007/978-3-031-30678-5_39
Wu, L., Li, J., Sun, P., Hong, R., Ge, Y., Wang, M.: Diffnet++: a neural influence and interest diffusion network for social recommendation. IEEE Trans. Knowl. Data Eng. 34(10), 4753–4766 (2020)
Yang, B., Lei, Y., Liu, J., Li, W.: Social collaborative filtering by trust. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1633–1647 (2016)
Yang, Y., et al.: Hyperbolic graph learning for social recommendation. IEEE Trans. Knowl. Data Eng. (2023)
Zhang, Y., Feng, F., He, X., Wei, T., Song, C., Ling, G., Zhang, Y.: Causal intervention for leveraging popularity bias in recommendation. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 11–20 (2021)
Zhao, Z., Chen, J., Zhou, S., He, X., Cao, X., Zhang, F., Wu, W.: Popularity bias is not always evil: Disentangling benign and harmful bias for recommendation. IEEE Trans. Knowl. Data Eng. (2022)
Zhou, W., Haq, A.U., Qiu, L., Akbar, J.: Multi-view social recommendation via matrix factorization with sub-linear convergence rate. Expert Syst. Appl. 237, 121687 (2024)
Acknowledgements
This work was supported by Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, China (Grant NO. 2022B1212010005), Shenzhen Research Council (Grant NO. Grant NO. WD20220811170253002) and Natural Science Foundation of Guangdong Province, China (Grant NO. 2024A1515010242).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, C., Li, G. (2024). BiasRec: A General Bias-Aware Social Recommendation Model. In: Onizuka, M., et al. Database Systems for Advanced Applications. DASFAA 2024. Lecture Notes in Computer Science, vol 14855. Springer, Singapore. https://doi.org/10.1007/978-981-97-5572-1_7
Download citation
DOI: https://doi.org/10.1007/978-981-97-5572-1_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5571-4
Online ISBN: 978-981-97-5572-1
eBook Packages: Computer ScienceComputer Science (R0)