Improving GNNs
Using Subgraphs for More Expressive GNNs
The expressive power of Message-Passing Graph Neural Networks is inherently limited due to their equivalence to the Weisfeiler-Lehman graph isomorphism test. Several concurrent recent works show that this limitation can be overcome by applying a GNN on a collection of subgraphs obtained by removing nodes or edges from the input…
Published in
14 min readDec 20, 2021