How Powerful are Graph Neural Networks?

by   Keyulu Xu, et al.
Stanford University

Graph Neural Networks (GNNs) for representation learning of graphs broadly follow a neighborhood aggregation framework, where the representation vector of a node is computed by recursively aggregating and transforming feature vectors of its neighboring nodes. Many GNN variants have been proposed and have achieved state-of-the-art results on both node and graph classification tasks. However, despite GNNs revolutionizing graph representation learning, there is limited understanding of their representational properties and limitations. Here, we present a theoretical framework for analyzing the expressive power of GNNs in capturing different graph structures. Our results characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures. We then develop a simple architecture that is provably the most expressive among the class of GNNs and is as powerful as the Weisfeiler-Lehman graph isomorphism test. We empirically validate our theoretical findings on a number of graph classification benchmarks, and demonstrate that our model achieves state-of-the-art performance.


page 1

page 2

page 3

page 4


Neighborhood Enlargement in Graph Neural Networks

Graph Neural Network (GNN) is an effective framework for representation ...

Graph Neural Networks Are More Powerful Than we Think

Graph Neural Networks (GNNs) are powerful convolutional architectures th...

A Hierarchy of Graph Neural Networks Based on Learnable Local Features

Graph neural networks (GNNs) are a powerful tool to learn representation...

Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification

We focus on graph classification using a graph neural network (GNN) mode...

k-hop Graph Neural Networks

Graph neural networks (GNNs) have emerged recently as a powerful archite...

Hierarchical Model Selection for Graph Neural Netoworks

Node classification on graph data is a major problem, and various graph ...

Path Neural Networks: Expressive and Accurate Graph Neural Networks

Graph neural networks (GNNs) have recently become the standard approach ...

Code Repositories


Geometric Deep Learning Extension Library for PyTorch

view repo


Graph neural network implementation using numpy

view repo


Project for Advance Machine Learning course. Innopolis University 2019.

view repo

Please sign up or login with your details

Forgot password? Click here to reset