mlsanityData to 7 Oct 2026

GraphDF: A Discrete Flow Model for Molecular Graph Generation

arXiv 2102.01189 ↗First posted 1 Feb 2021cs.LG cs.AIcited by 177

Not on the map. Why?

Cited by 46 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We consider the problem of molecular graph generation using deep models. While graphs are discrete, most existing methods use continuous latent variables, resulting in inaccurate modeling of discrete graph structures. In this work, we propose GraphDF, a novel discrete latent variable model for molecular graph generation based on normalizing flow methods. GraphDF uses invertible modulo shift transforms to map discrete latent variables to graph nodes and edges. We show that the use of discrete latent variables reduces computational costs and eliminates the negative effect of dequantization. Comprehensive experimental results show that GraphDF outperforms prior methods on random generation, property optimization, and constrained optimization tasks.

Key facts. Cited by 177 papers in the map (data through 7 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 1 Feb 2021.

Builds on

33 of 50 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2015Variational Inference with Normalizing Flowscited by 2,161
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  9. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  10. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  11. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  12. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
21 more
  1. 2019Graph U-Netscited by 489
  2. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  3. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  4. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
  5. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  6. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  7. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  8. 2017Grammar Variational Autoencodercited by 283
  9. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  10. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 183
  11. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  12. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 115
  13. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  14. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  15. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 80
  16. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
  17. 2019Discrete Flows: Invertible Generative Models of Discrete Datacited by 68
  18. 2018Molecular Hypergraph Grammar with its Application to Molecular Optimizationcited by 56
  19. 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46
  20. 2020Categorical Normalizing Flows via Continuous Transformationscited by 36
  21. 2019Graph Residual Flow for Molecular Graph Generationcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 32; 2023: 34; 2024: 42; 2025: 37; 2026: 22.

177 papers.

Sort:

By area:

  1. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  2. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  3. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  4. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  5. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  6. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  7. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 129
  8. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  9. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  10. 2022Periodic Graph Transformers for Crystal Material Property Predictioncited by 87
  11. 2024Position: Graph Foundation Models are Already Herecited by 84
  12. 2023Autoregressive Diffusion Model for Graph Generationcited by 82
38 more
  1. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 79
  2. 2024Variational Flow Matching for Graph Generationcited by 78
  3. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  4. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 72
  5. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  6. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  7. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  8. 2022MDM: Molecular Diffusion Model for 3D Molecule Generationcited by 58
  9. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 53
  10. 2023Graph Generation with Diffusion Mixturecited by 52
  11. 2022Reinforced Genetic Algorithm for Structure-based Drug Designcited by 46
  12. 2023Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generationcited by 46
  13. 2022GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generationcited by 43
  14. 2022LIMO: Latent Inceptionism for Targeted Molecule Generationcited by 40
  15. 2023Efficient Approximations of Complete Interatomic Potentials for Crystal Property Predictioncited by 37
  16. 2022Fast Graph Generation via Spectral Diffusioncited by 36
  17. 2023A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Materialcited by 34
  18. 2024Complete and Efficient Graph Transformers for Crystal Material Property Predictioncited by 34
  19. 2023Genetic algorithms are strong baselines for molecule generationcited by 31
  20. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  21. 2022Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentationscited by 28
  22. 2023A Latent Diffusion Model for Protein Structure Generationcited by 28
  23. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generationcited by 27
  24. 2023SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generationcited by 26
  25. 2024Diffusion Models in textitDe Novo Drug Designcited by 26
  26. 2023Towards Symmetry-Aware Generation of Periodic Materialscited by 25
  27. 2024Unifying Generation and Prediction on Graphs with Latent Graph Diffusioncited by 24
  28. 2023Data-centric Graph Learning: A Surveycited by 22
  29. 2022Graph Neural Networks for Moleculescited by 21
  30. 2023Domain-Agnostic Molecular Generation with Chemical Feedbackcited by 21
  31. 2022Task-Agnostic Graph Explanationscited by 20
  32. 2022FlowX: Towards Explainable Graph Neural Networks via Message Flowscited by 20
  33. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  34. 2023Drug Discovery with Dynamic Goal-aware Fragmentscited by 19
  35. 2022Target-aware Molecular Graph Generationcited by 18
  36. 2022NVDiff: Graph Generation through the Diffusion of Node Vectorscited by 18
  37. 2024Generative Modelling of Structurally Constrained Graphscited by 17
  38. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17

50 most cited of 177 All 177 (JSON)