An Attention-based Graph Neural Network for Heterogeneous Structural Learning

TL;DR

This paper introduces HetSANN, an attention-based graph neural network that directly encodes heterogeneous network structures without meta-paths, simplifying the process and improving representation quality.

Contribution

We propose a novel HetSANN model that captures heterogeneous information through attention mechanisms and entity space transformations, eliminating the need for meta-path design.

Findings

Achieves significant improvements over state-of-the-art methods

Effectively encodes heterogeneous information without meta-paths

Demonstrates robustness across multiple datasets

Abstract

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.