Rethinking Propagation for Unsupervised Graph Domain Adaptation

TL;DR

This paper reevaluates the role of propagation in GNNs for unsupervised graph domain adaptation, providing theoretical insights and proposing a new method called A2GNN that improves adaptation performance.

Contribution

It offers a theoretical analysis of GNN propagation effects in domain adaptation and introduces A2GNN, a novel approach that enhances transferability across graph domains.

Findings

Propagation layers influence domain adaptation effectiveness.

A2GNN outperforms existing methods on real-world datasets.

Theoretical bounds support the proposed propagation strategy.

Abstract

Unsupervised Graph Domain Adaptation (UGDA) aims to transfer knowledge from a labelled source graph to an unlabelled target graph in order to address the distribution shifts between graph domains. Previous works have primarily focused on aligning data from the source and target graph in the representation space learned by graph neural networks (GNNs). However, the inherent generalization capability of GNNs has been largely overlooked. Motivated by our empirical analysis, we reevaluate the role of GNNs in graph domain adaptation and uncover the pivotal role of the propagation process in GNNs for adapting to different graph domains. We provide a comprehensive theoretical analysis of UGDA and derive a generalization bound for multi-layer GNNs. By formulating GNN Lipschitz for k-layer GNNs, we show that the target risk bound can be tighter by removing propagation layers in source graph and stacking multiple propagation layers in target graph. Based on the empirical and theoretical analysis mentioned above, we propose a simple yet effective approach called A2GNN for graph domain adaptation. Through extensive experiments on real-world datasets, we demonstrate the effectiveness of our proposed A2GNN framework.