An Energy-Based View of Graph Neural Networks

2021/04/27 by John Y. Shin, Shin, John Y., Prathamesh Dharangutte +1
Computer Science · Materials Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG) #Machine Learning in Materials Science #cs.LG

paper · pdf · doi:10.48550/arxiv.2104.13492

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

openalex publication_date 2021/04/27 · arxiv created 2021/10/04 · arxiv updated 2021/10/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• A Theory of Generative ConvNet
• Semi-Supervised Classification with Graph Convolutional Networks
• How Powerful are Graph Neural Networks?
• Hierarchical Graph Pooling with Structure Learning
• Optimization of Graph Neural Networks with Natural Gradient Descent

Related

• How Powerful are Graph Neural Networks?
• On the choice of graph neural network architectures
• Energy Guided smoothness to improve Robustness in Graph Classification
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimization