2 papers
cs.LG2026
FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Network
Yonatan Sverdlov, Yair Davidson, Nadav Dym +1
Famously, the ability of Message Passing Neural Networks (MPNN) to distinguish between graphs is limited to graphs separable by the Weisfeiler-Lemann (WL) graph isomorphism test, a…
cs.LG2025
On the Hölder Stability of Multiset and Graph Neural Networks
Yair Davidson, Nadav Dym
Extensive research efforts have been put into characterizing and constructing maximally separating multiset and graph neural networks. However, recent empirical evidence suggests t…