Record link: 
http://hdl.handle.net/20.500.12708/210873
-
Title: 
Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
en
Citation: 
Paolino, R., Maskey, S., Welke, P., & Kutyniok, G. (2024). Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning. In 38th Conference on Neural Information Processing Systems (NeurIPS 2024). NeurIPS 2024, Vancouver, Canada. http://hdl.handle.net/20.500.12708/210873
-
Publication Type: 
Inproceedings - Full-Paper Contribution
en
Language: 
English
-
Authors: 
Paolino, Raffaele 
Maskey, Sohir 
Welke, Pascal 
Kutyniok, Gitta 
-
Organisational Unit: 
E194-06 - Forschungsbereich Machine Learning 
-
Published in: 
38th Conference on Neural Information Processing Systems (NeurIPS 2024) 
-
Date (published): 
2024
-
Event name: 
NeurIPS 2024 
en
Event date: 
10-Dec-2024 - 15-Dec-2024
-
Event place: 
Vancouver, Canada
-
Number of Pages: 
52
-
Peer reviewed: 
Yes
-
Keywords: 
Machine Learning; Graph Neural Networks; Weisfeiler-Leman (WL) Test; Homomorphism Counting; Theory and Expressivity in GNNs; Cactus Graphs
en
Abstract: 
We introduce r-loopy Weisfeiler-Leman (r-`WL), a novel hierarchy of graph isomorphism tests and a corresponding GNN framework, r-`MPNN, that can count cycles up to length r+2. Most notably, we show that r-`WL can count homomorphisms of cactus graphs. This extends 1-WL, which can only count homomorphisms of trees and, in fact, we prove that r-`WL is incomparable to k-WL for any fixed k. We empirically validate the expressive and counting power of r-`MPNN on several synthetic datasets and demonstrate the scalability and strong performance on various real-world datasets, particularly on sparse graphs.
en
Research Areas: 
Information Systems Engineering: 100%
-
Science Branch: 
1020 - Informatik: 90%
5020 - Wirtschaftswissenschaften: 10%
-
Appears in Collections:
Conference Paper

Show full item record

Page view(s)

23
checked on Feb 4, 2025

Google ScholarTM

Check