Source Free Unsupervised Graph Domain Adaptation

TL;DR

This paper introduces a novel source-free unsupervised graph domain adaptation method that leverages only a trained source model to improve node classification on unlabeled target graphs, addressing privacy constraints.

Contribution

It proposes the SOGA algorithm for source-free graph domain adaptation, enabling effective transfer without access to source data or labels, a scenario not addressed by prior methods.

Findings

SOGA improves Macro-F1 and Macro-AUC scores across four tasks.

Theoretical analysis confirms the effectiveness of the approach.

Empirical results demonstrate consistent performance gains.

Abstract

Graph Neural Networks (GNNs) have achieved great success on a variety of tasks with graph-structural data, among which node classification is an essential one. Unsupervised Graph Domain Adaptation (UGDA) shows its practical value of reducing the labeling cost for node classification. It leverages knowledge from a labeled graph (i.e., source domain) to tackle the same task on another unlabeled graph (i.e., target domain). Most existing UGDA methods heavily rely on the labeled graph in the source domain. They utilize labels from the source domain as the supervision signal and are jointly trained on both the source graph and the target graph. However, in some real-world scenarios, the source graph is inaccessible because of privacy issues. Therefore, we propose a novel scenario named Source Free Unsupervised Graph Domain Adaptation (SFUGDA). In this scenario, the only information we can leverage from the source domain is the well-trained source model, without any exposure to the source graph and its labels. As a result, existing UGDA methods are not feasible anymore. To address the non-trivial adaptation challenges in this practical scenario, we propose a model-agnostic algorithm called SOGA for domain adaptation to fully exploit the discriminative ability of the source model while preserving the consistency of structural proximity on the target graph. We prove the effectiveness of the proposed algorithm both theoretically and empirically. The experimental results on four cross-domain tasks show consistent improvements in the Macro-F1 score and Macro-AUC.