Disentangled Contrastive Learning for Social Recommendation

Wu，Jiahao1,2; Fan，Wenqi1; Chen，Jingfan1,3; Liu，Shengcai2; Li，Qing1; Tang，Ke2

10.1145/3511808.3557583

2022-10-17

International Conference on Information and Knowledge Management, Proceedings

4570-4574

Social recommendations utilize social relations to enhance the representation learning for recommendations. Most social recommendation models unify user representations for the user-item interactions (collaborative domain) and social relations (social domain). However, such an approach may fail to model the users' heterogeneous behavior patterns in two domains, impairing the expressiveness of user representations. In this work, to address such limitation, we propose a novel Disentangled contrastive learning framework for social Recommendations (DcRec). More specifically, we propose to learn disentangled users' representations from the item and social domains. Moreover, disentangled contrastive learning is designed to perform knowledge transfer between disentangled users' representations for social recommendations. Comprehensive experiments on various real-world datasets demonstrate the superiority of our proposed model.

collaborative learning disentangled learning self-supervised learning social recommendations

Others

English

2-s2.0-85140837559

Scopus

1.The Hong Kong Polytechnic University,Hong Kong,Hong Kong
2.Southern University of Science and Technology,Shenzhen,Guangdong,China
3.Centre for Artificial Intelligence and Robotics (HKISI-CAS),Hong Kong,Hong Kong

Wu，Jiahao,Fan，Wenqi,Chen，Jingfan,et al. Disentangled Contrastive Learning for Social Recommendation[C],2022:4570-4574.