mlsanityData to 14 Oct 2026

Adversarial Stein Training for Graph Energy Models

arXiv 2108.12982 ↗First posted 30 Aug 2021cs.LGcited by 0

Not on the map. Why?

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.

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

25 of 41 references.

References · 25

  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  4. 2017Wasserstein GANcited by 639
  5. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  6. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
  7. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  8. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  9. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  10. 2018Learning Deep Generative Models of Graphscited by 229
  11. 2016Adversarially Learned Inferencecited by 216
  12. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 116
13 more
  1. 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
  2. 2015Measuring Sample Quality with Stein's Methodcited by 94
  3. 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
  4. 2019Latent Normalizing Flows for Discrete Sequencescited by 67
  5. 2016Globally Normalized Transition-Based Neural Networkscited by 26
  6. 2020Energy-based models for atomic-resolution protein conformationscited by 20
  7. 2018Stein Neural Samplercited by 19
  8. 2016Operator Variational Inferencecited by 16
  9. 2019Kernel Stein Tests for Multiple Model Comparisoncited by 9
  10. 2017Learning neural trans-dimensional random field language models with noise-contrastive estimationcited by 7
  11. 2020Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Samplingcited by 6
  12. 2019Differential Equation Units: Learning Functional Forms of Activation Functions from Datacited by 1
  13. 2020Bosonic Random Walk Networks for Graph Learningcited by 1

Built on by

Not cited yet.