Graph out-of-distribution (OOD) generalization remains a major challenge in graph neural networks (GNNs). Invariant learning, aiming to extract invariant features across varied distributions, has ...

I'm looking for something that will let me specify a set of graphs, and easily look at the set of all forests generated by, say, a single cut, in different cases, e.g., if nodes are indistinguishable, ...

Graph out-of-distribution (OOD) generalization remains a major challenge in graph neural networks (GNNs). Invariant learning, aiming to extract ...