An Attention-based Graph Neural Network for Heterogeneous Structural Learning
This addresses the need for automated processing of heterogeneous graph data, eliminating the requirement for domain experts to design meta-path schemes, though it appears incremental as it builds on existing graph neural network and attention mechanisms.
The paper tackles the problem of graph representation learning for heterogeneous information networks (HINs) by proposing HetSANN, a model that directly encodes structural information without relying on meta-paths, achieving significant and consistent improvements over state-of-the-art solutions on three public datasets.
In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations. Most of the existing methods conducted on HIN revise homogeneous graph embedding models via meta-paths to learn low-dimensional vector space of HIN. In this paper, we propose a novel Heterogeneous Graph Structural Attention Neural Network (HetSANN) to directly encode structural information of HIN without meta-path and achieve more informative representations. With this method, domain experts will not be needed to design meta-path schemes and the heterogeneous information can be processed automatically by our proposed model. Specifically, we implicitly represent heterogeneous information using the following two methods: 1) we model the transformation between heterogeneous vertices through a projection in low-dimensional entity spaces; 2) afterwards, we apply the graph neural network to aggregate multi-relational information of projected neighborhood by means of attention mechanism. We also present three extensions of HetSANN, i.e., voices-sharing product attention for the pairwise relationships in HIN, cycle-consistency loss to retain the transformation between heterogeneous entity spaces, and multi-task learning with full use of information. The experiments conducted on three public datasets demonstrate that our proposed models achieve significant and consistent improvements compared to state-of-the-art solutions.