An Energy-Based View of Graph Neural Networks
This work addresses robustness issues in graph neural networks for applications like social network analysis or bioinformatics, but it is incremental as it builds on existing energy-based methods.
The authors tackled the problem of improving robustness in graph neural networks by integrating an energy-based framework, achieving comparable discriminative performance to standard GCNs while enhancing robustness.
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.