Node Feature Kernels Increase Graph Convolutional Network Robustness. (arXiv:2109.01785v2 [cs.LG] UPDATED)

The robustness of the much-used Graph Convolutional Networks (GCNs) to
perturbations of their input is becoming a topic of increasing importance. In
this paper, the random GCN is introduced for which a random matrix theory
analysis is possible. This analysis suggests that if the graph is sufficiently
perturbed, or in the extreme case random, then the GCN fails to benefit from
the node features. It is furthermore observed that enhancing the message
passing step in GCNs by adding the node …

arxiv graph network