HRS: Hybrid Recommendation System based on Attention Mechanism and Knowledge Graph Embedding

Traditional recommendation methods often have sparsity and cold start problems in real applications. Researchers found that introducing knowledge graphs into recommender systems as a kind of auxiliary information can alleviate these problems and improve the performance of the recommender systems. This paper put forward a Hybrid Recommendation System based on Attention Mechanism and Knowledge Graph Embedding (HRS). It uses crosscompress unit and preference propagation respectively to enrich the features of items and users. In this process, we use the attention mechanism and knowledge graph embedding to enhance the recommender system. After obtaining the user vector representation and the item vector representation, we can predict the probability of the user clicking on the item. The experiments on three datasets derived from the actual scenes demonstrate the competitiveness of HRS, compared with several state-of-the-art baselines in the recommendation.