Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
Abstract
In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Up to now, GNNs have only been evaluated empirically -- showing promising results. The following work investigates GNNs from a theoretical point of view and relates them to the -dimensional Weisfeiler-Leman graph isomorphism heuristic (-WL). We show that GNNs have the same expressiveness as the -WL in terms of distinguishing non-isomorphic (sub-)graphs. Hence, both algorithms also have the same shortcomings. Based on this, we propose a generalization of GNNs, so-called -dimensional GNNs (-GNNs), which can take higher-order graph structures at multiple scales into account. These higher-order structures play an essential role in the characterization of social networks and molecule graphs. Our experimental evaluation confirms our theoretical findings as well as confirms that higher-order information is useful in the task of graph classification and regression.
Keywords
Cite
@article{arxiv.1810.02244,
title = {Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks},
author = {Christopher Morris and Martin Ritzert and Matthias Fey and William L. Hamilton and Jan Eric Lenssen and Gaurav Rattan and Martin Grohe},
journal= {arXiv preprint arXiv:1810.02244},
year = {2021}
}
Comments
Extended version with proofs, accepted at AAAI 2019, added units of measurement of QM9 dataset into appendix, removed results from Wu et al., 2018 due to different units