Learning Distinct Relationship in Package Recommendation With Graph Attention Networks

Abstract

Recommendation systems have been widely developed and extensively used in various websites and platforms to promote products or services to interested users. However, in quite a few sale scenarios, the platform has the necessity to display users a series of items, which is called package recommendation. There is very little research in this area. This article develops a novel and realistic package recommendation system named package graph attention network (PGAT) based on graph neural network. PGAT integrates users, items, and packages to build a unified heterogeneous graph and treat them as a whole. PGAT incorporates an attention mechanism in the first-order neighborhood aggregation operation, which can differentiate the weight of different neighbor nodes to the center node. By performing graph attention and graph convolution operations on the tripartite graph, PGAT can learn node embeddings more expressively and address the problem of data sparse to a large extent. Extensive experiment results on two real-world datasets validate the outstanding performance of PGAT, which is superior to the state-of-the-art baselines by 0.77%–10.12%.