# Adversarial Stein Training for Graph Energy Models

arXiv: https://arxiv.org/abs/2108.12982 · HTML: https://mlsanity.com/paper/2108.12982/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 30 Aug 2021.

## Builds on (most cited first, 25 of 25)

- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [Permutation Invariant Graph Generation via Score-Based Generative Modeling](https://mlsanity.com/paper/2003.00638/) (2020)
- [A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation](https://mlsanity.com/paper/1602.03253/) (2016)
- [Learning Deep Generative Models of Graphs](https://mlsanity.com/paper/1803.03324/) (2018)
- [Adversarially Learned Inference](https://mlsanity.com/paper/1606.00704/) (2016)
- [GraphNVP: An Invertible Flow Model for Generating Molecular Graphs](https://mlsanity.com/paper/1905.11600/) (2019)
- [Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach](https://mlsanity.com/paper/1706.05674/) (2017)
- [Measuring Sample Quality with Stein's Method](https://mlsanity.com/paper/1506.03039/) (2015)
- [LanczosNet: Multi-Scale Deep Graph Convolutional Networks](https://mlsanity.com/paper/1901.01484/) (2019)
- [Latent Normalizing Flows for Discrete Sequences](https://mlsanity.com/paper/1901.10548/) (2019)
- [Globally Normalized Transition-Based Neural Networks](https://mlsanity.com/paper/1603.06042/) (2016)
- [Energy-based models for atomic-resolution protein conformations](https://mlsanity.com/paper/2004.13167/) (2020)
- [Stein Neural Sampler](https://mlsanity.com/paper/1810.03545/) (2018)
- [Operator Variational Inference](https://mlsanity.com/paper/1610.09033/) (2016)
- [Kernel Stein Tests for Multiple Model Comparison](https://mlsanity.com/paper/1910.12252/) (2019)
- [Learning neural trans-dimensional random field language models with noise-contrastive estimation](https://mlsanity.com/paper/1710.10739/) (2017)
- [Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling](https://mlsanity.com/paper/2002.05616/) (2020)
- [Differential Equation Units: Learning Functional Forms of Activation Functions from Data](https://mlsanity.com/paper/1909.03069/) (2019)
- [Bosonic Random Walk Networks for Graph Learning](https://mlsanity.com/paper/2101.00082/) (2020)

## Abstract (arXiv)

Learning distributions over graph-structured data is a challenging task with many applications in biology and chemistry. In this work we use an energy-based model (EBM) based on multi-channel graph neural networks (GNN) to learn permutation invariant unnormalized density functions on graphs. Unlike standard EBM training methods our approach is to learn the model via minimizing adversarial stein discrepancy. Samples from the model can be obtained via Langevin dynamics based MCMC. We find that this approach achieves competitive results on graph generation compared to benchmark models.