Heterogeneous Graph Neural Network for Personalized Session-Based Recommendation with User-Session Constraints

TL;DR

This paper introduces a heterogeneous graph neural network that integrates user and session data with attention mechanisms to improve personalized session-based recommendations, demonstrating superior performance on real-world datasets.

Contribution

It proposes a novel heterogeneous graph neural network model that effectively incorporates user-session relationships and constraints for enhanced recommendation accuracy.

Findings

Outperforms existing methods on multiple datasets

Effectively models user preferences within sessions

Utilizes attention mechanisms for better relationship capturing

Abstract

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 representation that includes session representations generated by user. In this paper, we consider various relationships in graph created by sessions through Heterogeneous attention network. Constraints also force user representations to consider the user's preferences presented in the session. It seeks to increase performance through additional optimization in the training process. The proposed model outperformed other methods on various real-world datasets.