Answers are grounded in this paper and cite their sources.
Explains the expressiveness of graph neural networks through combinatorial algorithms and logics, indicating their potential in machine learning on graphs.
Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs. It has recently been shown that the expressiveness of GNNs can be characterised precisely by the combinatorial Weisfeiler-Leman algorithms and by finite variable counting logics. The correspondence has even led to new, higher-order GNNs corresponding to the WL algorithm in higher dimensions.The purpose of this paper is to explain these descriptive characterisations of GNNs.
No takes yet. Share an insight, caveat, or question.
Martin Grohe (2021) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: