Social-Enhanced Explainable Recommendation With Knowledge Graph

Recommendation systems are of crucial importance due to their wide applications. Knowledge graph (KG) enabled recommendation schemes have attracted great attention due to their superior performance and interpretability. However, the rich social information is not exploited for those systems, which limits the recommendation performance . In this paper, a novel explainable recommendation scheme is proposed by exploiting our designed social enhanced knowledge graph attention network (SKGAN). The hidden relations among users and items are learned and used for recommendation with the collaborative KG (CKG) and the user social graph (USG). Moreover, the high-order semantic information in both CKG and USG are obtained by using the graph convolution networks (GCNs) and the node level attention algorithm. Furthermore, a graph level user-specific attention algorithm is proposed to capture the user personalized preference between CKG and USG. Extensive experiment results demonstrate that normalized discounted cumulative gain (NDCG), precision, recall and hits ratio (HR) achieved with our proposed recommendation system are the best among those obtained with the state-of-the-art benchmark recommendation systems.