Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

by   Giorgos Bouritsas, et al.

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying graph. It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Lehman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and count graph substructures. On the other hand, there is significant empirical evidence, e.g. in network science and bioinformatics, that substructures are often informative for downstream tasks, suggesting that it is desirable to design GNNs capable of leveraging this important source of information. To this end, we propose a novel topologically-aware message passing scheme based on subgraph isomorphism counting. We show that our architecture allows incorporating domain-specific inductive biases and that it is strictly more expressive than the WL test. Importantly, in contrast to recent works on the expressivity of GNNs, we do not attempt to adhere to the WL hierarchy; this allows us to retain multiple attractive properties of standard GNNs such as locality and linear complexity, while being able to disambiguate even hard instances of graph isomorphism. We extensively evaluate our method on graph classification and regression tasks and show state-of-the-art results on multiple datasets including molecular graphs and social networks.



There are no comments yet.


page 1

page 2

page 3

page 4


Twin Weisfeiler-Lehman: High Expressive GNNs for Graph Classification

The expressive power of message passing GNNs is upper-bounded by Weisfei...

AutoGraph: Automated Graph Neural Network

Graphs play an important role in many applications. Recently, Graph Neur...

Can graph neural networks count substructures?

The ability to detect and count certain substructures in graphs is impor...

Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results

While massage passing based Graph Neural Networks (GNNs) have become inc...

Directional Graph Networks

In order to overcome the expressive limitations of graph neural networks...

An Analysis of Attentive Walk-Aggregating Graph Neural Networks

Graph neural networks (GNNs) have been shown to possess strong represent...

Equivariant Graph Mechanics Networks with Constraints

Learning to reason about relations and dynamics over multiple interactin...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.