Multi-component graph collaborative filtering using auxiliary information for TV program recommendation

Abstract

Recommendation systems for TV programs play an important role in alleviating the information overload problem. Existing TV program recommendation methods either do not aggregate neighborhood information well to capture collaborative signals from interaction data, or fail to make good use of auxiliary information, because they ignore the heterogeneity of different entities and relationships. In this paper, we propose a multi-component graph collaborative filtering recommendation based on auxiliary information, which learns representations of user and program through heterogeneous data modeling and information propagation on graphs. We extract homogeneous subgraphs from the heterogeneous graph based on multiple symmetric meta-paths, learn the components of the node representation by performing graph convolution on the homogeneous subgraphs, and finally combine the components to obtain the complete user representation and program representation. Experiments on real-world datasets show that our approach can effectively improve the performance of TV program recommendations compared to the existing baselines.