A Survey on The Expressive Power of Graph Neural Networks

TL;DR

This survey reviews the expressive capabilities of graph neural networks (GNNs), discussing their limitations, recent theoretical insights, and variants designed to enhance their power in graph learning tasks.

Contribution

It provides a comprehensive overview of the theoretical expressive power of GNNs and introduces variants that address their limitations.

Findings

GNNs have known theoretical limitations in expressiveness.

Recent variants of GNNs can overcome some of these limitations.

The survey summarizes current understanding and future directions in GNN expressiveness.

Abstract

Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have been revealed recently. Consequently, many GNN models have been proposed to overcome these limitations. In this survey, we provide a comprehensive overview of the expressive power of GNNs and provably powerful variants of GNNs.