Skip to main content
2 votes
Accepted

Relevance of Weisfeiler–Lehman Graph Isomorphism Test limitation for Graph Neural Networks

Firstly, as already stated in the Wikipedia quote: Observing that a type of GNN is as expressive as the Weisfeiler–Lehman (WL) Test, means in practice that two graphs $\mathcal{G}_1$ and $\mathcal{G}...
Chillston's user avatar
  • 1,748
1 vote

Why readout operation in message passing graph neural nets have to be invariant to node permutations?

It is necessary for GCNs / MPNNs to be invariant to node permutations in order to generalize properly. Firstly, node permutation means that you reindex the nodes. The edges also use this new indexing, ...
Chillston's user avatar
  • 1,748

Only top scored, non community-wiki answers of a minimum length are eligible