Improving Expressivity of Graph Neural Networks

04/08/2020
by   Stanisław Purgał, et al.
0

We propose a Graph Neural Network with greater expressive power than commonly used GNNs - not constrained to only differentiate between graphs that Weisfeiler-Lehman test recognizes to be non-isomorphic. We use a graph attention network with expanding attention window that aggregates information from nodes exponentially far away. We also use partially random initial embeddings, allowing differentiation between nodes that would otherwise look the same. This could cause problem with a traditional dropout mechanism, therefore we use a "head dropout", randomly ignoring some attention heads rather than some dimensions of the embedding.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/06/2022

Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks

Recent work shows that the expressive power of Graph Neural Networks (GN...
research
12/17/2022

Analyzing the Traffic of MANETs using Graph Neural Networks

Graph Neural Networks (GNNs) have been taking role in many areas, thanks...
research
06/15/2020

Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification

The attention mechanism has demonstrated superior performance for infere...
research
09/09/2019

Distance-Preserving Graph Embeddings from Random Neural Features

We present Graph Random Neural Features (GRNF), a novel embedding method...
research
07/25/2019

Graph Neural Lasso for Dynamic Network Regression

In this paper, we will study the dynamic network regression problem, whi...
research
10/10/2016

A Dynamic Window Neural Network for CCG Supertagging

Combinatory Category Grammar (CCG) supertagging is a task to assign lexi...
research
04/11/2022

How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision

Attention mechanism in graph neural networks is designed to assign large...

Please sign up or login with your details

Forgot password? Click here to reset