<div class="csl-bib-body">
<div class="csl-entry">Paolino, R., Maskey, S., Welke, P., & Kutyniok, G. (2024, May 11). <i>Weisfeiler and Leman go Loopy: A New Hierarchy for Graph Representational Learning</i> [Poster Presentation]. ICLR 2024 Workshop Bridging the Gap Between Practice and Theory in Deep Learning, Austria. https://doi.org/10.34726/6959</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/203184
-
dc.identifier.uri
https://doi.org/10.34726/6959
-
dc.description
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-WLfor 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. The code is available online.
-
dc.description.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. The code is available online.
-
dc.description.sponsorship
WWTF Wiener Wissenschafts-, Forschu und Technologiefonds
-
dc.language.iso
en
-
dc.rights.uri
http://creativecommons.org/licenses/by-nc-sa/4.0/
-
dc.subject
Graph Neural Networks
en
dc.subject
Weisfeiler Leman
en
dc.subject
Expressivity
en
dc.title
Weisfeiler and Leman go Loopy: A New Hierarchy for Graph Representational Learning
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.rights.license
Creative Commons Namensnennung - Nicht-kommerziell - Weitergabe unter gleichen Bedingungen 4.0 International
de
dc.rights.license
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
en
dc.identifier.doi
10.34726/6959
-
dc.contributor.affiliation
Ludwig-Maximilians-Universität München, Germany
-
dc.contributor.affiliation
Ludwig-Maximilians-Universität München, Germany
-
dc.relation.grantno
ICT22-059
-
dc.type.category
Poster Presentation
-
tuw.project.title
Structured Data Learning with Generalized Similarities
-
tuw.researchTopic.id
I5
-
tuw.researchTopic.name
Visual Computing and Human-Centered Technology
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E194-06 - Forschungsbereich Machine Learning
-
tuw.author.orcid
0000-0002-9691-6712
-
tuw.author.orcid
0000-0002-2123-3781
-
tuw.author.orcid
0000-0001-9738-2487
-
dc.rights.identifier
CC BY-NC-SA 4.0
de
dc.rights.identifier
CC BY-NC-SA 4.0
en
tuw.event.name
ICLR 2024 Workshop Bridging the Gap Between Practice and Theory in Deep Learning
en
tuw.event.startdate
11-05-2024
-
tuw.event.enddate
11-05-2024
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.country
AT
-
tuw.event.presenter
Maskey, Sohir
-
tuw.event.presenter
Welke, Pascal
-
tuw.event.track
Single Track
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.openairecristype
http://purl.org/coar/resource_type/c_18co
-
item.openaccessfulltext
Open Access
-
item.openairetype
conference poster not in proceedings
-
item.fulltext
with Fulltext
-
item.mimetype
application/pdf
-
item.languageiso639-1
en
-
item.grantfulltext
open
-
item.cerifentitytype
Publications
-
crisitem.author.dept
Ludwig-Maximilians-Universität München
-
crisitem.author.dept
Ludwig-Maximilians-Universität München
-
crisitem.author.dept
E194-06 - Forschungsbereich Machine Learning
-
crisitem.author.dept
Ludwig-Maximilians-Universität München
-
crisitem.author.orcid
0000-0002-9691-6712
-
crisitem.author.orcid
0000-0002-2123-3781
-
crisitem.author.orcid
0000-0001-9738-2487
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.project.funder
WWTF Wiener Wissenschafts-, Forschu und Technologiefonds
