Weisfeiler-Lehman goes dynamic: an analysis of the expressive power of graph neural networks for attributed and dynamic graphs

DOI10.1016/J.NEUNET.2024.106213MaRDI QIDQ6536113zbMATH OpenFDO

Authors Silvia Beddar-Wiesing, Giuseppe Alessio D'Inverno, Caterina Graziani, Veronica Lachi, Alice Moallemy-Oureh, Franco Scarselli, Josephine Maria Thomas

Publication date 27 March 2024

Published in Neural Networks (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1016/J.NEUNET.2024.106213

zbMATH Keywords

dynamic graphsGNN expressivitygraph neural networkunfolding treesWeisfeiler-Lehman test

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• The logic of graph neural networks
• \(k\)-hop graph neural networks
• Theory of graph neural networks: representation and learning
• Graph rewriting for graph neural networks

Cites work

• Representation learning for dynamic graphs: a survey
• Universal covers, color refinement, and two-variable counting logic: lower bounds for the depth
• Weisfeiler-Lehman graph kernels

Cited in

(3)

• Graph rewriting for graph neural networks
• The logic of graph neural networks
• Mesh-informed reduced order models for aneurysm rupture risk prediction

This page was built for publication: Weisfeiler-Lehman goes dynamic: an analysis of the expressive power of graph neural networks for attributed and dynamic graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6536113)