Homophily Enhanced Graph Domain Adaptation

TL;DR

This paper emphasizes the importance of graph homophily in graph domain adaptation, revealing its discrepancies across benchmarks and proposing a novel alignment method that improves transfer performance.

Contribution

It introduces the first analysis of homophily discrepancies in GDA and proposes a homophily alignment algorithm using mixed filters to enhance domain transfer.

Findings

Homophily discrepancies exist in benchmark datasets.

Homophily discrepancies negatively impact GDA performance.

The proposed method improves GDA results across various benchmarks.

Abstract

Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. In this paper, we highlight the significance of graph homophily, a pivotal factor for graph domain alignment, which, however, has long been overlooked in existing approaches. Specifically, our analysis first reveals that homophily discrepancies exist in benchmarks. Moreover, we also show that homophily discrepancies degrade GDA performance from both empirical and theoretical aspects, which further underscores the importance of homophily alignment in GDA. Inspired by this finding, we propose a novel homophily alignment algorithm that employs mixed filters to smooth graph signals, thereby effectively capturing and mitigating homophily discrepancies between graphs. Experimental results on a variety of benchmarks verify the effectiveness of our method.