Heterogeneous Graph Neural Network for Session-Based Recommendation with User-Session Constraint

The recommendation system provides users with an appropriate limit of recent online large amounts of information. Session-based recommendation, a sub-area of recommender systems, attempts to recommend items by interpreting sessions that consist of sequences of items. Recently, research to include user information in these sessions is progress. However, it is difficult to generate high-quality user information that includes session information generated by user. In this paper, we consider various relationships in graph created by sessions through HAN. Constraints also force user information to take into account information from the session. It seeks to increase performance through additional optimization in the training process. The proposed model outperformed other methods on various real-world data sets.