An Energy-Based View of Graph Neural Networks
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
11 of 16 references.
References · 11
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
- 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 242
- 2016A Theory of Generative ConvNetcited by 174
- 2019What Can Neural Networks Reason About?cited by 159
- 2019Hierarchical Graph Pooling with Structure Learningcited by 81
- 2020Optimization of Graph Neural Networks with Natural Gradient Descentcited by 26
- 2019Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patternscited by 22
- 2019Energy-based Graph Convolutional Networks for Scoring Protein Docking Modelscited by 5
- 2019GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networkscited by 3
Built on by
Citing papers per year: 2022: 1.
1 paper.