An Energy-Based View of Graph Neural Networks

TL;DR

This paper introduces an energy-based framework for graph neural networks to enhance robustness while maintaining classification performance, opening new research directions.

Contribution

It proposes a novel energy-based method for GNNs that jointly models features and adjacency, improving robustness over standard GCNs.

Findings

Comparable accuracy to standard GCNs

Improved robustness against adversarial attacks

New framework for energy-based GNNs

Abstract

Graph neural networks are a popular variant of neural networks that work with graph-structured data. In this work, we consider combining graph neural networks with the energy-based view of Grathwohl et al. (2019) with the aim of obtaining a more robust classifier. We successfully implement this framework by proposing a novel method to ensure generation over features as well as the adjacency matrix and evaluate our method against the standard graph convolutional network (GCN) architecture (Kipf & Welling (2016)). Our approach obtains comparable discriminative performance while improving robustness, opening promising new directions for future research for energy-based graph neural networks.