<div class="csl-bib-body">
<div class="csl-entry">Brasoveanu, A. D., Jogl, F., Welke, P., & Thiessen, M. (2023, November 27). <i>Extending Graph Neural Networks with Global Features</i> [Poster Presentation]. Learning on Graphs Conference 2023, Austria. https://doi.org/10.34726/5281</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/190327
-
dc.identifier.uri
https://doi.org/10.34726/5281
-
dc.description.abstract
A common approach to boost the predictive performance of message passing graph neural networks (MPNNs) is to attach additional features to nodes. In contrast, we propose to use expressive global graph features. This is motivated by the limited expressivity of MPNNs resulting in an inability to compute certain global graph properties, like the Wiener index and Hosoya index. Such global graph features are well known in fields like chemoinformatics but seem to be overlooked by the GNN community. We propose an architecture which extends graph embeddings learned by MPNNs with global graph features, for example, topological indices describing the entire graph. Analyzing different global graph features, we show that certain global features like the Wiener index increase the expressivity of MPNNs, while others like the Zagreb indices do not. Our first experiments indicate that adding global graph features improves the performance of MPNNs on molecular benchmark datasets.
en
dc.language.iso
en
-
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
-
dc.subject
Machine Learning
en
dc.subject
Graph Learning
en
dc.title
Extending Graph Neural Networks with Global Features
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
10.34726/5281
-
dc.contributor.affiliation
TU Wien, Austria
-
dc.type.category
Poster Presentation
-
tuw.researchTopic.id
I4
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.linking
https://openreview.net/forum?id=aisVQy6R2k
-
tuw.publication.orgunit
E194-06 - Forschungsbereich Machine Learning
-
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
-
tuw.event.startdate
27-11-2023
-
tuw.event.enddate
30-11-2023
-
tuw.event.online
Online
-
tuw.event.type
Event for scientific audience
-
tuw.event.country
AT
-
tuw.event.presenter
Brasoveanu, Andrei Dragos
-
tuw.event.presenter
Jogl, Fabian
-
tuw.event.presenter
Welke, Pascal
-
tuw.event.presenter
Thiessen, Maximilian
-
tuw.presentation.online
Online
-
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
TU Wien
-
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.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
