Social Boosted Recommendation with Folded Bipartite Network Embedding
With the prevalence of online social platforms, social recommendation has emerged as a promising direction. However, the available social relations among users are usually extremely sparse and noisy, which may lead to an inferior recommendation performance. To alleviate this problem, this paper exploits the implicit higher-order social influences and dependencies among users to enhance social recommendations. In this paper, we propose a novel embedding method for general bipartite graphs, which defines inter-class message passing between explicit relations and intra-class message passing between implicit higher-order relations via a novel sequential modelling paradigm. Inspired by recent advances in self-attention-based sequence modelling, the proposed model features a self-attentive representation learning on the user-user implicit relations. Moreover, this paper also explores the inductive embedding learning for social recommendation problems to improve the recommendation performance in cold-start settings. The proposed inductive learning paradigm for social recommendation enables embedding inference for those cold-start users and items (unseen during training) as long as they are linked to existing nodes in the original network during evaluation. Extensive experiments on real-world datasets demonstrate the superiority of our method and validate that higher-order implicit relationship among users is beneficial to improving social recommendations.
Branch: CSE Domain: Data Mining
Developed In: Java