Enhancing Node-Level Graph Domain Adaptation by Alleviating Local Dependency

TL;DR

This paper addresses the challenge of unsupervised graph domain adaptation by identifying local dependencies among node features as a key obstacle, and proposes decorrelation techniques to improve transferability and performance.

Contribution

It introduces a theoretical analysis linking local node feature dependencies to conditional shift in GDA, and proposes decorrelation methods to enhance transferability.

Findings

Significant performance improvements over baseline GDA methods.

Theoretical evidence connecting local dependencies to conditional shift.

Visualizations showing reduced intra-class distances in learned representations.

Abstract

Recent years have witnessed significant advancements in machine learning methods on graphs. However, transferring knowledge effectively from one graph to another remains a critical challenge. This highlights the need for algorithms capable of applying information extracted from a source graph to an unlabeled target graph, a task known as unsupervised graph domain adaptation (GDA). One key difficulty in unsupervised GDA is conditional shift, which hinders transferability. In this paper, we show that conditional shift can be observed only if there exists local dependencies among node features. To support this claim, we perform a rigorous analysis and also further provide generalization bounds of GDA when dependent node features are modeled using markov chains. Guided by the theoretical findings, we propose to improve GDA by decorrelating node features, which can be specifically implemented through decorrelated GCN layers and graph transformer layers. Our experimental results demonstrate the effectiveness of this approach, showing not only substantial performance enhancements over baseline GDA methods but also clear visualizations of small intra-class distances in the learned representations. Our code is available at https://github.com/TechnologyAiGroup/DFT