Random Features Strengthen Graph Neural Networks

02/08/2020
by   Ryoma Sato, et al.
66

Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks. Recently, the limitations of the expressive power of various GNN models have been revealed. For example, GNNs cannot distinguish some non-isomorphic graphs and they cannot learn efficient graph algorithms, and several GNN models have been proposed to overcome these limitations. In this paper, we demonstrate that GNNs become powerful just by adding a random feature to each node. We prove that the random features enable GNNs to learn almost optimal polynomial-time approximation algorithms for the minimum dominating set problem and maximum matching problem in terms of the approximation ratio. The main advantage of our method is that it can be combined with off-the-shelf GNN models with slight modifications. Through experiments, we show that the addition of random features enables GNNs to solve various problems that normal GNNs, including GCNs and GINs, cannot solve.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/09/2020

A Survey on The Expressive Power of Graph Neural Networks

Graph neural networks (GNNs) are effective machine learning models for v...
research
05/24/2019

Approximation Ratios of Graph Neural Networks for Combinatorial Problems

In this paper, from a theoretical perspective, we study how powerful gra...
research
05/27/2021

On the Universality of Graph Neural Networks on Large Random Graphs

We study the approximation power of Graph Neural Networks (GNNs) on late...
research
03/11/2021

Should Graph Neural Networks Use Features, Edges, Or Both?

Graph Neural Networks (GNNs) are the first choice for learning algorithm...
research
01/03/2022

Two-level Graph Neural Network

Graph Neural Networks (GNNs) are recently proposed neural network struct...
research
02/15/2021

Topological Graph Neural Networks

Graph neural networks (GNNs) are a powerful architecture for tackling gr...
research
11/11/2021

DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

This paper studies Dropout Graph Neural Networks (DropGNNs), a new appro...

Please sign up or login with your details

Forgot password? Click here to reset