Generalizing Graph Neural Networks on Out-Of-Distribution Graphs

arXiv:2111.10657v3 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) are proposed without considering the agnostic distribution shifts between training and testing graphs, inducing the degeneration of the generalization ability of GNNs on Out-Of-Distribution (OOD) settings. The fundamental reason for such degeneration is that most GNNs are developed based on the I.I.D hypothesis. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. However, such spurious …

abstract arxiv cs.ai cs.lg distribution gnns graph graph neural networks graphs hypothesis networks neural networks reason testing training type