# An Energy-Based View of Graph Neural Networks

arXiv: https://arxiv.org/abs/2104.13492 · HTML: https://mlsanity.com/paper/2104.13492/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [A Theory of Generative ConvNet](https://mlsanity.com/paper/1602.03264/) (2016)
- [What Can Neural Networks Reason About?](https://mlsanity.com/paper/1905.13211/) (2019)
- [Hierarchical Graph Pooling with Structure Learning](https://mlsanity.com/paper/1911.05954/) (2019)
- [Optimization of Graph Neural Networks with Natural Gradient Descent](https://mlsanity.com/paper/2008.09624/) (2020)
- [Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns](https://mlsanity.com/paper/1909.11975/) (2019)
- [Energy-based Graph Convolutional Networks for Scoring Protein Docking Models](https://mlsanity.com/paper/1912.12476/) (2019)
- [GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks](https://mlsanity.com/paper/1910.02107/) (2019)

## Built on by (most cited first, 1 of 1)

- [Robust Graph Representation Learning via Predictive Coding](https://mlsanity.com/paper/2212.04656/) (2022)

## Abstract (arXiv)

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.