GkGNN extends GNN message passing from neighborhoods to covers via category theory, with the Sieve Neural Networks instantiation achieving zero failures on SRG, CSL, and BREC isomorphism benchmarks.
Wang, M Zhang, ”An Empirical Study of Realized GNN Expressive- ness,” in Proceedings of Machine Learning Research 235:52134-52155
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNs
GkGNN extends GNN message passing from neighborhoods to covers via category theory, with the Sieve Neural Networks instantiation achieving zero failures on SRG, CSL, and BREC isomorphism benchmarks.