Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks

Christopher Morris, Martin Ritzert, Matthias Fey et al.

2019 · 1,208 citations

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 1-dimensional Weisfeiler-Leman graph isomorphism heuristic (1-WL). We show that GNNs have the same expressiveness as the 1-WL in terms of distinguishing non-isomorphic (sub-)graphs. Hence, both algorithms also have the same shortcomings. Based…

Read the paper →

Explore this paper's citation graph on Constellation.