(2) We can use various types of relationships in the KG to propagate user preferences and increase the diversity of recommendation results. (1) We can use the extensive item and item attribute information in the KG to supplement the item representation and improve recommendation accuracy. Compared with other recommendation methods, introducing a KG into recommender systems has three advantages. In a recommendation scenario, the entity can be an item (movie) or an attribute of the item (movie’s director). A KG is a heterogeneous information network, containing multiple nodes and multiple connected edges between nodes, where the nodes are different entities in the KG, and the edges are relationships between entities. In recent studies, researchers have used the correlation between items and item attributes to construct a knowledge graph (KG) for the recommendation, with good results. We have verified that KCNR has excellent recommendation performance through extensive experiments in three real-life scenes: movies, books, and music. In addition, considering the relevance of items to entities in the knowledge graph, KCNR has designed an information complementarity module, which automatically shares potential interaction characteristics of items and entities, and enables items and entities to complement the available information. With the above processing, KCNR can automatically discover structural and associative semantic information in the knowledge graph, and capture users’ latent distant personalized preferences, by propagating them across the knowledge graph. Similarly, KCNR samples multiple-hop neighbors of item entities in the knowledge graph, and has a bias to aggregate the neighborhood information, to enhance the item embedding representation. Specifically, KCNR first encodes prior information about the user–item interaction, and obtains the user’s different knowledge neighbors by propagating them in the knowledge graph, and uses a knowledge-aware attention network to distinguish and aggregate the contributions of the different neighbors in the knowledge graph, as a way to enrich the user’s description. In this paper, in order to address the insufficient representation of user and item embeddings in existing knowledge graph-based recommendation methods, a knowledge-aware enhanced network, combining neighborhood information recommendation (KCNR), is proposed. In recent years, the application of knowledge graphs to alleviate cold start and data sparsity problems of users and items in recommendation systems, has aroused great interest.
0 Comments
Leave a Reply. |