Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework

04/06/2020
by   Floris Geerts, et al.
0

In this paper we cast neural networks defined on graphs as message-passing neural networks (MPNNs) in order to study the distinguishing power of different classes of such models. We are interested in whether certain architectures are able to tell vertices apart based on the feature labels given as input with the graph. We consider two variants of MPNNS: anonymous MPNNs whose message functions depend only on the labels of vertices involved; and degree-aware MPNNs in which message functions can additionally use information regarding the degree of vertices. The former class covers a popular formalisms for computing functions on graphs: graph neural networks (GNN). The latter covers the so-called graph convolutional networks (GCNs), a recently introduced variant of GNNs by Kipf and Welling. We obtain lower and upper bounds on the distinguishing power of MPNNs in terms of the distinguishing power of the Weisfeiler-Lehman (WL) algorithm. Our results imply that (i) the distinguishing power of GCNs is bounded by the WL algorithm, but that they are one step ahead; (ii) the WL algorithm cannot be simulated by "plain vanilla" GCNs but the addition of a trade-off parameter between features of the vertex and those of its neighbours (as proposed by Kipf and Welling themselves) resolves this problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/04/2021

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

The pairwise interaction paradigm of graph machine learning has predomin...
12/14/2020

A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks

In this paper, we derive generalization bounds for the two primary class...
06/24/2022

A Topological characterisation of Weisfeiler-Leman equivalence classes

Graph Neural Networks (GNNs) are learning models aimed at processing gra...
10/06/2020

Reward Propagation Using Graph Convolutional Networks

Potential-based reward shaping provides an approach for designing good r...
06/04/2018

Deep Graphs

We propose an algorithm for deep learning on networks and graphs. It rel...
03/17/2022

On the expressive power of message-passing neural networks as global feature map transformers

We investigate the power of message-passing neural networks (MPNNs) in t...
01/23/2019

Typed Graph Networks

Recently, the deep learning community has given growing attention to neu...