DeepAI AI Chat
Log In Sign Up

Can graph neural networks count substructures?

by   Zhengdao Chen, et al.

The ability to detect and count certain substructures in graphs is important for solving many tasks on graph-structured data, especially in the contexts of computational chemistry and biology as well as social network analysis. Inspired by this, we propose to study the expressive power of graph neural networks (GNNs) via their ability to count attributed graph substructures, extending recent works that examine their power in graph isomorphism testing. We distinguish between two types of substructure counting: matching-count and containment-count, and establish mostly negative answers for a wide class of GNN architectures. Specifically, we prove that Message Passing Neural Networks (MPNNs), Weisfeiler-Lehman (WL) and 2-Invariant Graph Networks (2-IGNs) cannot perform matching-count of substructures consisting of 3 or more nodes, while they can perform containment-count of star-shaped substructures. We also provide partial results for k-WL and k-IGNs. We then conduct experiments that support several of the theoretical results, and demonstrate that local relational pooling strategies inspired by Murphy et al. (2019) are more effective for substructure counting. In addition, we prove that WL and 2-IGNs are equivalent in distinguishing non-isomorphic graphs, partly answering an open problem raised in Maron et al. (2019).


page 1

page 2

page 3

page 4


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

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

Learning to Count Isomorphisms with Graph Neural Networks

Subgraph isomorphism counting is an important problem on graphs, as many...

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

While Graph Neural Networks (GNNs) have achieved remarkable results in a...

Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels

Graph neural networks (GNNs) have achieved tremendous success in graph m...

Provably Powerful Graph Networks

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to ...

Technical report: Graph Neural Networks go Grammatical

This paper proposes a new GNN design strategy. This strategy relies on C...

Residual Gated Graph ConvNets

Graph-structured data such as functional brain networks, social networks...