Pairwise Alignment Improves Graph Domain Adaptation

arXiv:2403.01092v1 Announce Type: new
Abstract: Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model training differs significantly from the graph used for testing. This work delves into Graph Domain Adaptation (GDA) to address the unique complexities of distribution shifts over graph data, where interconnected data points experience shifts in features, labels, and in particular, connecting patterns. We propose a novel, theoretically principled method, Pairwise Alignment (Pair-Align) …

abstract alignment applications arxiv challenges complexities cs.lg distribution domain domain adaptation gda graph graph-based inference objects pivotal testing training type work world