LGDMNEJun 6, 2023

Fine-grained Expressivity of Graph Neural Networks

arXiv:2306.03698v230 citationsh-index: 23
Originality Incremental advance
AI Analysis

This work provides a theoretical foundation for understanding graph similarity and MPNN expressivity, which is foundational for advancing graph machine learning, though it is incremental in extending existing combinatorial techniques to continuous settings.

The paper tackles the problem of characterizing the expressive power of message-passing graph neural networks (MPNNs) beyond binary graph isomorphism, by extending the 1-WL test and MPNNs to graphons, providing a continuous framework that reveals which graphs MPNNs can distinguish and their difficulty levels, with empirical validation showing randomly initialized MPNNs achieve competitive performance without training.

Numerous recent works have analyzed the expressive power of message-passing graph neural networks (MPNNs), primarily utilizing combinatorial techniques such as the $1$-dimensional Weisfeiler-Leman test ($1$-WL) for the graph isomorphism problem. However, the graph isomorphism objective is inherently binary, not giving insights into the degree of similarity between two given graphs. This work resolves this issue by considering continuous extensions of both $1$-WL and MPNNs to graphons. Concretely, we show that the continuous variant of $1$-WL delivers an accurate topological characterization of the expressive power of MPNNs on graphons, revealing which graphs these networks can distinguish and the level of difficulty in separating them. We identify the finest topology where MPNNs separate points and prove a universal approximation theorem. Consequently, we provide a theoretical framework for graph and graphon similarity combining various topological variants of classical characterizations of the $1$-WL. In particular, we characterize the expressive power of MPNNs in terms of the tree distance, which is a graph distance based on the concept of fractional isomorphisms, and substructure counts via tree homomorphisms, showing that these concepts have the same expressive power as the $1$-WL and MPNNs on graphons. Empirically, we validate our theoretical findings by showing that randomly initialized MPNNs, without training, exhibit competitive performance compared to their trained counterparts. Moreover, we evaluate different MPNN architectures based on their ability to preserve graph distances, highlighting the significance of our continuous $1$-WL test in understanding MPNNs' expressivity.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes