PuSH - Publikationsserver des Helmholtz Zentrums München

Morris, C.* ; Lipman, Y.* ; Maron, H.* ; Rieck, B. ; Kriege, N.M.* ; Grohe, M.* ; Fey, M.* ; Borgwardt, K.*

Weisfeiler and Leman go Machine Learning: The Story so far.

J. Mach. Learn. Res. 24:333 (2023)
Creative Commons Lizenzvertrag
In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm's use in a machine-learning setting, focusing on the supervised regime. We discuss the theoretical background, show how to use it for supervised graph and node representation learning, discuss recent extensions, and outline the algorithm's connection to (permutation-)equivariant neural architectures. Moreover, we give an overview of current applications and future directions to stimulate further research.
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Review
Korrespondenzautor
Schlagwörter Machine learning for graphs; Graph neural networks; Weisfeiler-Leman algorithm; expressivity; equivariance; Sherali-adams Relaxations; Neural-network; Graph Isomorphism; Darc System; Kernels; Classification; Information; Generation; Logics
ISSN (print) / ISBN 1532-4435
e-ISSN 1533-7928
Zeitschrift Journal of Machine Learning Research
Quellenangaben Band: 24, Heft: , Seiten: , Artikelnummer: 333 Supplement: ,
Verlag MIT Press
Verlagsort 31 Gibbs St, Brookline, Ma 02446 Usa
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Institute of AI for Health (AIH)
Förderungen Hightech Agenda Bavaria
Bavarian State Government
RWTH Junior Principal Investigator Fellowship under Germany's Excellence Strategy