mlsanityData to 7 Oct 2026

GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

arXiv 2001.09382 ↗First posted 26 Jan 2020cs.LG stat.MLcited by 301

Not on the map. Why?

Cited by 68 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention. The problem is challenging since it requires not only generating chemically valid molecular structures but also optimizing their chemical properties in the meantime. Inspired by the recent progress in deep generative models, in this paper we propose a flow-based autoregressive model for graph generation called GraphAF. GraphAF combines the advantages of both autoregressive and flow-based approaches and enjoys: (1) high model flexibility for data density estimation; (2) efficient parallel computation for training; (3) an iterative sampling process, which allows leveraging chemical domain knowledge for valency checking. Experimental results show that GraphAF is able to generate 68% chemically valid molecules even without chemical knowledge rules and 100% valid molecules with chemical rules. The training process of GraphAF is two times faster than the existing state-of-the-art approach GCPN. After fine-tuning the model for goal-directed property optimization with reinforcement learning, GraphAF achieves state-of-the-art performance on both chemical property optimization and constrained property optimization.

Key facts. Cited by 301 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 45; 2022: 60; 2023: 59; 2024: 58; 2025: 47; 2026: 32.

301 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  3. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  4. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  5. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  6. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  7. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  8. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 177
  9. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  10. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  11. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  12. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 129
38 more
  1. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  2. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  3. 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 96
  4. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  5. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
  6. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  7. 2023Autoregressive Diffusion Model for Graph Generationcited by 82
  8. 2024Variational Flow Matching for Graph Generationcited by 78
  9. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  10. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  11. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
  12. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  13. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  14. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  15. 2023Equivariant Flow Matching with Hybrid Probability Transportcited by 59
  16. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
  17. 2021ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoningcited by 58
  18. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  19. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 53
  20. 2021Differentiable Scaffolding Tree for Molecular Optimizationcited by 53
  21. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 53
  22. 2023Graph Generation with Diffusion Mixturecited by 52
  23. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  24. 2022Graph-based Molecular Representation Learningcited by 51
  25. 2022Regression Transformer: Concurrent sequence regression and generation for molecular language modelingcited by 49
  26. 2024How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Frameworkcited by 48
  27. 2025Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithmscited by 47
  28. 2022Reinforced Genetic Algorithm for Structure-based Drug Designcited by 46
  29. 2023Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generationcited by 46
  30. 2023Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Needcited by 46
  31. 2021Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spacescited by 45
  32. 2022TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discoverycited by 45
  33. 2022GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generationcited by 43
  34. 2022LIMO: Latent Inceptionism for Targeted Molecule Generationcited by 40
  35. 2021The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Predictioncited by 39
  36. 2023Efficient Approximations of Complete Interatomic Potentials for Crystal Property Predictioncited by 37
  37. 2022Fast Graph Generation via Spectral Diffusioncited by 36
  38. 2023A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Materialcited by 34

50 most cited of 301 All 301 (JSON)