Learning on heterogeneous graphs using high-order relations

TL;DR

This paper introduces a novel method for learning on heterogeneous graphs that avoids meta-paths by decomposing the graph into relation-type graphs and combining them with attention mechanisms, leading to improved vertex classification performance.

Contribution

The proposed approach captures higher-order relations without meta-paths by decomposing and combining relation-type graphs with attention, outperforming existing methods.

Findings

Outperforms state-of-the-art baselines in vertex classification

Effectively captures higher-order relations in heterogeneous graphs

Preserves edge heterogeneity and directionality

Abstract

A heterogeneous graph consists of different vertices and edges types. Learning on heterogeneous graphs typically employs meta-paths to deal with the heterogeneity by reducing the graph to a homogeneous network, guide random walks or capture semantics. These methods are however sensitive to the choice of meta-paths, with suboptimal paths leading to poor performance. In this paper, we propose an approach for learning on heterogeneous graphs without using meta-paths. Specifically, we decompose a heterogeneous graph into different homogeneous relation-type graphs, which are then combined to create higher-order relation-type representations. These representations preserve the heterogeneity of edges and retain their edge directions while capturing the interaction of different vertex types multiple hops apart. This is then complemented with attention mechanisms to distinguish the importance of the relation-type based neighbors and the relation-types themselves. Experiments demonstrate that our model generally outperforms other state-of-the-art baselines in the vertex classification task on three commonly studied heterogeneous graph datasets.