mlsanityData to 7 Oct 2026

GraphEBM: Molecular Graph Generation with Energy-Based Models

arXiv 2102.00546 ↗First posted 31 Jan 2021cs.LGcited by 85

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We note that most existing approaches for molecular graph generation fail to guarantee the intrinsic property of permutation invariance, resulting in unexpected bias in generative models. In this work, we propose GraphEBM to generate molecular graphs using energy-based models. In particular, we parameterize the energy function in a permutation invariant manner, thus making GraphEBM permutation invariant. We apply Langevin dynamics to train the energy function by approximately maximizing likelihood and generate samples with low energies. Furthermore, to generate molecules with a desirable property, we propose a simple yet effective strategy, which pushes down energies with flexible degrees according to the properties of corresponding molecules. Finally, we explore the use of GraphEBM for generating molecules with multiple objectives in a compositional manner. Comprehensive experimental results on random, goal-directed, and compositional generation tasks demonstrate the effectiveness of our proposed method.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). Builds on 58 of its 87 references that are in the map. First posted on arXiv 31 Jan 2021.

Builds on

58 of 87 references.

References · 58

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2016Density estimation using Real NVPcited by 2,029
  10. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
38 more
  1. 2019Simplifying Graph Convolutional Networkscited by 1,470
  2. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  3. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  4. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  5. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  6. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  7. 2020Simple and Deep Graph Convolutional Networkscited by 857
  8. 2018Link Prediction Based on Graph Neural Networkscited by 829
  9. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  10. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  11. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  12. 2019Graph U-Netscited by 489
  13. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  14. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  15. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  16. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
  17. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  18. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  19. 2018Invariant and Equivariant Graph Networkscited by 339
  20. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  21. 2020Towards Deeper Graph Neural Networkscited by 296
  22. 2017Grammar Variational Autoencodercited by 283
  23. 2021How to Train Your Energy-Based Modelscited by 271
  24. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  25. 2018Learning Deep Generative Models of Graphscited by 227
  26. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  27. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 183
  28. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  29. 2016A Theory of Generative ConvNetcited by 174
  30. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 127
  31. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 115
  32. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  33. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  34. 2019Graph Convolutional Networks with EigenPoolingcited by 94
  35. 2020Non-Local Graph Neural Networkscited by 91
  36. 2020Line Graph Neural Networks for Link Predictioncited by 89
  37. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 80
  38. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 16; 2023: 18; 2024: 18; 2025: 16; 2026: 10.

85 papers.

Sort:

By area:

  1. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  2. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  3. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  4. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  5. 2022SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generatorscited by 96
  6. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  7. 2022Periodic Graph Transformers for Crystal Material Property Predictioncited by 87
  8. 2023Autoregressive Diffusion Model for Graph Generationcited by 82
  9. 2024Variational Flow Matching for Graph Generationcited by 78
  10. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  11. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  12. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
38 more
  1. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  2. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  3. 2021Differentiable Scaffolding Tree for Molecular Optimizationcited by 53
  4. 2022Reinforced Genetic Algorithm for Structure-based Drug Designcited by 46
  5. 2023Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generationcited by 46
  6. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  7. 2022Fast Graph Generation via Spectral Diffusioncited by 36
  8. 2024Complete and Efficient Graph Transformers for Crystal Material Property Predictioncited by 34
  9. 2023Genetic algorithms are strong baselines for molecule generationcited by 31
  10. 2022Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentationscited by 28
  11. 2023A Latent Diffusion Model for Protein Structure Generationcited by 28
  12. 2023Towards Symmetry-Aware Generation of Periodic Materialscited by 25
  13. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  14. 2023Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihoodcited by 19
  15. 2024Energy-based Automated Model Evaluationcited by 16
  16. 2023A Simple and Scalable Representation for Graph Generationcited by 15
  17. 2025Periodic Materials Generation using Text-Guided Joint Diffusion Modelcited by 15
  18. 2022Machine Learning for a Sustainable Energy Futurecited by 14
  19. 2024LLM-Based Multi-Agent Systems are Scalable Graph Generative Modelscited by 11
  20. 2021Partition and Code: learning how to compress graphscited by 10
  21. 2024A Graph is Worth K Words: Euclideanizing Graph using Pure Transformercited by 10
  22. 2024Improving Molecular Graph Generation with Flow Matching and Optimal Transportcited by 10
  23. 2025Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphscited by 9
  24. 2023Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shiftingcited by 8
  25. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  26. 2024DrugCLIP: Contrastive Drug-Disease Interaction For Drug Repurposingcited by 7
  27. 2022Gradient-Guided Importance Sampling for Learning Binary Energy-Based Modelscited by 6
  28. 2023Hyperbolic Graph Diffusion Modelcited by 6
  29. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
  30. 2024Zero Shot Molecular Generation via Similarity Kernelscited by 6
  31. 2025HOG-Diff: Higher-Order Guided Diffusion for Graph Generationcited by 6
  32. 2022Robust Graph Representation Learning via Predictive Codingcited by 5
  33. 2023Diffusing on Two Levels and Optimizing for Multiple Properties: A Novel Approach to Generating Molecules with Desirable Propertiescited by 5
  34. 2024CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learningcited by 5
  35. 2024Hitchhiker's guide on the relation of Energy-Based Models with other generative models, sampling and statistical physics: a comprehensive reviewcited by 5
  36. 2025Synergistic Benefits of Joint Molecule Generation and Property Predictioncited by 5
  37. 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generationcited by 4
  38. 2025Gradient GA: Gradient Genetic Algorithm for Drug Molecular Designcited by 4

50 most cited of 85 All 85 (JSON)