An Energy-Based View of Graph Neural Networks

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.

arXiv comment-Updated with new references. -Accepted to the ICLR2021 EBM Workshop

References in corpus (8)

• Semi-Supervised Classification with Graph Convolutional Networks
• How Powerful are Graph Neural Networks?
• A Theory of Generative ConvNet
• Hierarchical Graph Pooling with Structure Learning
• Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• Energy-based Graph Convolutional Networks for Scoring Protein Docking Models
• Optimization of Graph Neural Networks with Natural Gradient Descent
• GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks