DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation
arXiv:2604.10882v1 Announce Type: new
Abstract: Graph Neural Network pretraining is pivotal for leveraging unlabeled graph data. However, generalizing across heterogeneous domains remains a major challenge due to severe distribution shifts. Existing m…