3 citations · 3 across the 1 of their papers we have counts for
2 papers
cs.LG2025
What Expressivity Theory Misses: Message Passing Complexity for GNNs
Niklas Kemper, Tom Wollschläger, Stephan Günnemann
Expressivity theory, characterizing which graphs a GNN can distinguish, has become the predominant framework for analyzing GNNs, with new models striving for higher expressivity. H…
cs.LG2024★ 3 cited
Expressivity and Generalization: Fragment-Biases for Molecular GNNs
Tom Wollschläger, Niklas Kemper, Leon Hetzel +2
Although recent advances in higher-order Graph Neural Networks (GNNs) improve the theoretical expressiveness and molecular property predictive performance, they often fall short of…