<div class="csl-bib-body">
<div class="csl-entry">Bause, F., Jogl, F., Indri, P., Drucks, T., Penz, D., Kriege, N., Gärtner, T., Welke, P., & Thiessen, M. (2023, December 1). <i>Maximally Expressive GNNs for Outerplanar Graphs</i> [Poster Presentation]. Learning-on-Graphs Conference 2023: Local Meetup, München, Germany. https://doi.org/10.34726/5344</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/191403
-
dc.identifier.uri
https://doi.org/10.34726/5344
-
dc.description
We propose a linear time graph transformation that enables the Weisfeiler-Leman (WL) test and message passing graph neural networks (MPNNs) to be maximally expressive on outerplanar graphs. Our approach is motivated by the fact that most pharmaceutical molecules correspond to outerplanar graphs. Existing research predominantly enhances the expressivity of graph neural networks without specific graph families in mind. This often leads to methods that are impractical due to their computational complexity. In contrast, the restriction to outerplanar graphs enables us to encode the Hamiltonian cycle of each biconnected component in linear time. As the main contribution of the paper we prove that our method achieves maximum expressivity on outerplanar graphs. Experiments confirm that our graph transformation improves the predictive performance of MPNNs on molecular benchmark datasets at negligible computational overhead.
-
dc.description.abstract
We propose a linear time graph transformation that enables the Weisfeiler-Leman (WL) test and message passing graph neural networks (MPNNs) to be maximally expressive on outerplanar graphs. Our approach is motivated by the fact that most pharmaceutical molecules correspond to outerplanar graphs. Existing research predominantly enhances the expressivity of graph neural networks without specific graph families in mind. This often leads to methods that are impractical due to their computational complexity. In contrast, the restriction to outerplanar graphs enables us to encode the Hamiltonian cycle of each biconnected component in linear time. As the main contribution of the paper we prove that our method achieves maximum expressivity on outerplanar graphs. Experiments confirm that our graph transformation improves the predictive performance of MPNNs on molecular benchmark datasets at negligible computational overhead.
en
dc.description.sponsorship
WWTF Wiener Wissenschafts-, Forschu und Technologiefonds
-
dc.language.iso
en
-
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
-
dc.subject
outerplanar graphs
en
dc.subject
expressive graph
en
dc.subject
representation
en
dc.subject
learning
en
dc.title
Maximally Expressive GNNs for Outerplanar Graphs
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.rights.license
Creative Commons Namensnennung 4.0 International
de
dc.rights.license
Creative Commons Attribution 4.0 International
en
dc.identifier.doi
10.34726/5344
-
dc.contributor.affiliation
University of Vienna, Austria
-
dc.contributor.affiliation
University of Vienna, Austria
-
dc.relation.grantno
ICT22-059
-
dc.type.category
Poster Presentation
-
tuw.project.title
Structured Data Learning with Generalized Similarities
-
tuw.researchTopic.id
I4
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E194-06 - Forschungsbereich Machine Learning
-
tuw.author.orcid
0000-0003-2645-947X
-
tuw.author.orcid
0000-0001-5985-9213
-
tuw.author.orcid
0000-0002-2123-3781
-
tuw.author.orcid
0000-0001-9333-2685
-
dc.rights.identifier
CC BY 4.0
de
dc.rights.identifier
CC BY 4.0
en
tuw.event.name
Learning-on-Graphs Conference 2023: Local Meetup
en
dc.description.sponsorshipexternal
Vienna Science and Technology Fund (WWTF)
-
dc.relation.grantnoexternal
VRG19-009
-
tuw.event.startdate
30-11-2023
-
tuw.event.enddate
01-12-2023
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
München
-
tuw.event.country
DE
-
tuw.event.institution
Technische Universität München
-
tuw.event.presenter
Indri, Patrick
-
tuw.event.presenter
Drucks, Tamara
-
tuw.event.presenter
Welke, Pascal
-
tuw.event.track
Single Track
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.openairetype
conference poster not in proceedings
-
item.languageiso639-1
en
-
item.cerifentitytype
Publications
-
item.mimetype
application/pdf
-
item.fulltext
with Fulltext
-
item.openaccessfulltext
Open Access
-
item.grantfulltext
open
-
item.openairecristype
http://purl.org/coar/resource_type/c_18co
-
crisitem.project.funder
WWTF Wiener Wissenschafts-, Forschu und Technologiefonds
-
crisitem.project.grantno
ICT22-059
-
crisitem.author.dept
University of Vienna
-
crisitem.author.dept
E192-02 - Forschungsbereich Databases and Artificial Intelligence
-
crisitem.author.dept
E194-06 - Forschungsbereich Machine Learning
-
crisitem.author.dept
E194-06 - Forschungsbereich Machine Learning
-
crisitem.author.dept
E194-06 - Forschungsbereich Machine Learning
-
crisitem.author.dept
University of Vienna
-
crisitem.author.dept
E194-06 - Forschungsbereich Machine Learning
-
crisitem.author.dept
E194-06 - Forschungsbereich Machine Learning
-
crisitem.author.dept
E194-06 - Forschungsbereich Machine Learning
-
crisitem.author.orcid
0000-0003-2645-947X
-
crisitem.author.orcid
0000-0001-5985-9213
-
crisitem.author.orcid
0000-0002-2123-3781
-
crisitem.author.orcid
0000-0001-9333-2685
-
crisitem.author.parentorg
E192 - Institut für Logic and Computation
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
