<div class="csl-bib-body">
<div class="csl-entry">Jogl, F., Thiessen, M., & Gärtner, T. (2022). Weisfeiler and Leman Return with Graph Transformations. In <i>18th International Workshop on Mining and Learning with Graphs - Accepted Papers</i>. 18th International Workshop on Mining and Learning with Graphs, Grenoble, France. https://doi.org/10.34726/3829</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/175714
-
dc.identifier.uri
https://doi.org/10.34726/3829
-
dc.description.abstract
We propose novel graph transformations that allow standard message passing to achieve state-of-the-art expressiveness and predictive performance. Message passing graph neural networks are known to have limited expressiveness in distinguishing graphs. To mitigate this, one can either change message passing or modify the graphs. Changing message passing is powerful but requires significant changes to existing implementations and cannot easily be combined with other approaches. Modifying the graph requires no changes to the learning algorithm and works directly with off-the-shelf implementations. In this paper, we propose novel graph transformations and compare them to the state-of-the-art. We prove that they are at least as expressive as corresponding message passing algorithms when combined with the Weisfeiler-Leman test or a sufficiently powerful graph neural network. Furthermore, we empirically demonstrate that these transformations lead to competitive results on molecular graph datasets.
en
dc.language.iso
en
-
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
-
dc.subject
Machine Learning
en
dc.subject
Graph Neural Networks
en
dc.subject
Expressiveness
en
dc.title
Weisfeiler and Leman Return with Graph Transformations
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.rights.license
Creative Commons Namensnennung 4.0 International
de
dc.rights.license
Creative Commons Attribution 4.0 International
en
dc.identifier.doi
10.34726/3829
-
dc.type.category
Full-Paper Contribution
-
tuw.booktitle
18th International Workshop on Mining and Learning with Graphs - Accepted Papers
-
tuw.peerreviewed
true
-
tuw.researchTopic.id
I4a
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.linking
https://www.mlgworkshop.ml/
-
tuw.linking
https://openreview.net/forum?id=Oq5mzL-3SUV
-
tuw.publication.orgunit
E194-06 - Forschungsbereich Machine Learning
-
dc.description.numberOfPages
24
-
tuw.author.orcid
0000-0001-9333-2685
-
tuw.author.orcid
0000-0001-5985-9213
-
dc.rights.identifier
CC BY 4.0
de
dc.rights.identifier
CC BY 4.0
en
tuw.event.name
18th International Workshop on Mining and Learning with Graphs
en
tuw.event.startdate
23-09-2022
-
tuw.event.enddate
23-09-2022
-
tuw.event.online
Hybrid
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Grenoble
-
tuw.event.country
FR
-
tuw.event.presenter
Jogl, Fabian
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.fulltext
with Fulltext
-
item.cerifentitytype
Publications
-
item.mimetype
application/pdf
-
item.openairecristype
http://purl.org/coar/resource_type/c_5794
-
item.languageiso639-1
en
-
item.openaccessfulltext
Open Access
-
item.openairetype
conference paper
-
item.grantfulltext
open
-
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
0000-0001-9333-2685
-
crisitem.author.orcid
0000-0001-5985-9213
-
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