Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
MCML Authors
Raffaele Paolino
Sohir Maskey
Gitta Kutyniok
Prof. Dr.
Core PI
Abstract
Raffaele Paolino
Sohir Maskey
Gitta Kutyniok
Prof. Dr.
Core PI
Abstract
We introduce r-loopy Weisfeiler-Leman (r-ℓWL), a novel hierarchy of graph isomorphism tests and a corresponding GNN framework, r-ℓMPNN, that can count cycles up to length r+2. Most notably, we show that r-ℓWL can count homomorphisms of cactus graphs. This strictly extends classical 1-WL, which can only count homomorphisms of trees and, in fact, is incomparable to k-WL for any fixed k. We empirically validate the expressive and counting power of the proposed r-ℓMPNN on several synthetic datasets and present state-of-the-art predictive performance on various real-world datasets.
inproceedings PMW+24
NeurIPS 2024
38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024.
Authors
R. Paolino • S. Maskey • P. Welke • G. KutyniokLinks
DOI GitHubResearch Area
BibTeXKey: PMW+24