Saved in:
Bibliographic Details
Main Authors: Paolino, Raffaele, Maskey, Sohir, Welke, Pascal, Kutyniok, Gitta
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.13749
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913572954570752
author Paolino, Raffaele
Maskey, Sohir
Welke, Pascal
Kutyniok, Gitta
author_facet Paolino, Raffaele
Maskey, Sohir
Welke, Pascal
Kutyniok, Gitta
contents We introduce $r$-loopy Weisfeiler-Leman ($r$-$\ell{}$WL), a novel hierarchy of graph isomorphism tests and a corresponding GNN framework, $r$-$\ell{}$MPNN, that can count cycles up to length $r + 2$. Most notably, we show that $r$-$\ell{}$WL 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 $r$-$\ell{}$MPNN on several synthetic datasets and present state-of-the-art predictive performance on various real-world datasets. The code is available at https://github.com/RPaolino/loopy
format Preprint
id arxiv_https___arxiv_org_abs_2403_13749
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
Paolino, Raffaele
Maskey, Sohir
Welke, Pascal
Kutyniok, Gitta
Machine Learning
We introduce $r$-loopy Weisfeiler-Leman ($r$-$\ell{}$WL), a novel hierarchy of graph isomorphism tests and a corresponding GNN framework, $r$-$\ell{}$MPNN, that can count cycles up to length $r + 2$. Most notably, we show that $r$-$\ell{}$WL 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 $r$-$\ell{}$MPNN on several synthetic datasets and present state-of-the-art predictive performance on various real-world datasets. The code is available at https://github.com/RPaolino/loopy
title Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
topic Machine Learning
url https://arxiv.org/abs/2403.13749