AI RESEARCH

CGRL: Causal-Guided Representation Learning for Graph Out-of-Distribution Generalization

arXiv CS.LG

ArXi:2603.24304v1 Announce Type: cross Graph Neural Networks (GNNs) have achieved impressive performance in graph-related tasks. However, they suffer from poor generalization on out-of-distribution (OOD) data, as they tend to learn spurious correlations. Such correlations present a phenomenon that GNNs fail to stably learn the mutual information between prediction representations and ground-truth labels under OOD settings.