Graph attentive matrix factorization for social recommendation

Abstract

AbstractRecommender systems commonly encounter with the problems of data sparsity and cold start. Recently, social recommendation has emerged with the rapid expansion of social platforms, offering an opportunity to alleviate such two obstacles. Nevertheless, there are still two key limitations in existing studies. From the perspective of model design, previous social recommenders only consider the influence of a user's direct friends or uniformly treat the influences from different friends. From the perspective of model learning, most of them apply a sampling‐based optimization strategy, which requires high‐quality positive and negative samples. In light of the aforementioned limitations, we propose a new probabilistic method, named Graph Attentive Matrix Factorization (GAMF). Our method not only explicitly captures high‐order social relationships, but also adopts an attention mechanism to automatically pick up different influences between friends. Moreover, we develop an efficient optimization algorithm to learn model parameters in a non‐sampling manner. Extensive experiments on four large‐scale datasets show the superiority of GAMF over state‐of‐the‐art recommenders, especially under the cold start scenario.