Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
About
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 on this, we propose a generalization of GNNs, so-called $k$-dimensional GNNs ($k$-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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Graph Classification | PROTEINS | Accuracy75.5 | 1383 | |
| Graph Classification | MUTAG | Accuracy86.1 | 1229 | |
| Node Classification | Chameleon | Accuracy50.55 | 936 | |
| Node Classification | Pubmed | Accuracy89.35 | 902 | |
| Node Classification | Cornell | Accuracy89.19 | 900 | |
| Node Classification | Texas | Accuracy0.7838 | 859 | |
| Graph Classification | NCI1 | Accuracy76.2 | 707 | |
| Graph Classification | IMDB-B | Accuracy74.2 | 455 | |
| Node Classification | Roman-Empire | Accuracy71.45 | 398 | |
| Node Classification | Ogbn-arxiv | Accuracy45.55 | 337 |