On the Cross-type Homophily of Heterogeneous Graphs: Understanding and Unleashing

TL;DR

This paper introduces a new metric called Cross-Type Homophily Ratio (CHR) to better understand homophily in heterogeneous graphs and proposes a graph editing method, CTHGE, that leverages CHR to enhance HGNN performance significantly.

Contribution

The paper presents CHR, a novel homophily metric for heterogeneous graphs, and CTHGE, a graph editing technique guided by CHR to improve HGNN accuracy.

Findings

CHR effectively captures cross-type homophily in HGs.

CTHGE improves HGNN performance by up to 25%.

Extensive experiments validate the approach across multiple datasets and models.

Abstract

Homophily, the tendency of similar nodes to connect, is a fundamental phenomenon in network science and a critical factor in the performance of graph neural networks (GNNs). While existing studies primarily explore homophily in homogeneous graphs, where nodes share the same type, real-world networks are often more accurately modeled as heterogeneous graphs (HGs) with diverse node types and intricate cross-type interactions. This structural diversity complicates the analysis of homophily, as traditional homophily metrics fail to account for distinct label spaces across node types. To address this limitation, we introduce the Cross-Type Homophily Ratio (CHR), a novel metric that quantifies homophily based on the similarity of target information across different node types. Additionally, we propose Cross-Type Homophily-guided Graph Editing (CTHGE), a novel method for improving heterogeneous graph neural networks (HGNNs) performance by optimizing cross-type connectivity using Cross-Type Homophily Ratio. Extensive experiments on five HG datasets with nine HGNNs validate the effectiveness of CTHGE, which delivers a maximum relative performance improvement of over 25% for HGNNs on node classification tasks, offering a fresh perspective on cross-type homophily in HGs learning.