Structure-Attribute Transformations with Markov Chain Boost Graph Domain Adaptation
This addresses label scarcity in graph learning across different domains, representing an incremental improvement over existing graph domain adaptation methods.
The paper tackles the problem of structural heterogeneity in graph domain adaptation by proposing SATMC, a framework that aligns distributions through both structure and attribute transformations with a private information reduction mechanism. Experiments on nine cross-domain datasets show SATMC outperforms state-of-the-art methods in cross-network node classification.
Graph domain adaptation has gained significant attention in label-scarce scenarios across different graph domains. Traditional approaches to graph domain adaptation primarily focus on transforming node attributes over raw graph structures and aligning the distributions of the transformed node features across networks. However, these methods often struggle with the underlying structural heterogeneity between distinct graph domains, which leads to suboptimal distribution alignment. To address this limitation, we propose Structure-Attribute Transformation with Markov Chain (SATMC), a novel framework that sequentially aligns distributions across networks via both graph structure and attribute transformations. To mitigate the negative influence of domain-private information and further enhance the model's generalization, SATMC introduces a private domain information reduction mechanism and an empirical Wasserstein distance. Theoretical proofs suggest that SATMC can achieve a tighter error bound for cross-network node classification compared to existing graph domain adaptation methods. Extensive experiments on nine pairs of publicly available cross-domain datasets show that SATMC outperforms state-of-the-art methods in the cross-network node classification task. The code is available at https://github.com/GiantZhangYT/SATMC.