DeepAI AI Chat
Log In Sign Up

The expressive power of kth-order invariant graph networks

by   Floris Geerts, et al.

The expressive power of graph neural network formalisms is commonly measured by their ability to distinguish graphs. For many formalisms, the k-dimensional Weisfeiler-Leman (k-WL) graph isomorphism test is used as a yardstick. In this paper we consider the expressive power of kth-order invariant (linear) graph networks (k-IGNs). It is known that k-IGNs are expressive enough to simulate k-WL. This means that for any two graphs that can be distinguished by k-WL, one can find a k-IGN which also distinguishes those graphs. The question remains whether k-IGNs can distinguish more graphs than k-WL. This was recently shown to be false for k=2. Here, we generalise this result to arbitrary k. In other words, we show that k-IGNs are bounded in expressive power by k-WL. This implies that k-IGNs and k-WL are equally powerful in distinguishing graphs.


page 1

page 2

page 3

page 4


Walk Message Passing Neural Networks and Second-Order Graph Neural Networks

The expressive power of message passing neural networks (MPNNs) is known...

Weisfeiler and Lehman Go Measurement Modeling: Probing the Validity of the WL Test

The expressive power of graph neural networks is usually measured by com...

Graph Homomorphism Convolution

In this paper, we study the graph classification problem from the graph ...

Fine-grained Expressivity of Graph Neural Networks

Numerous recent works have analyzed the expressive power of message-pass...

Three iterations of (d-1)-WL test distinguish non isometric clouds of d-dimensional points

The Weisfeiler–Lehman (WL) test is a fundamental iterative algorithm for...

Weisfeiler and Leman Go Relational

Knowledge graphs, modeling multi-relational data, improve numerous appli...

Expectation-Complete Graph Representations with Homomorphisms

We investigate novel random graph embeddings that can be computed in exp...