AI RESEARCH
Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNs
arXiv CS.LG
•
ArXi:2412.08835v2 Announce Type: replace Graph Neural Networks (GNNs) are almost universally built on a single primitive: the neighborhood. Regardless of architectural variations, message passing ultimately aggregates over neighborhoods, which intrinsically limits expressivity and often yields power no stronger than the Weisfeiler-Lehman (WL) test. In this work, we challenge this primitive. We