mlsanityData to 7 Oct 2026

Generative Flow Networks for Discrete Probabilistic Modeling

arXiv 2202.01361 ↗First posted 3 Feb 2022cs.LG stat.MLcited by 113

Not on the map. Why?

Abstract (arXiv)

We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data. Building upon the theory of generative flow networks (GFlowNets), we model the generation process by a stochastic data construction policy and thus amortize expensive MCMC exploration into a fixed number of actions sampled from a GFlowNet. We show how GFlowNets can approximately perform large-block Gibbs sampling to mix between modes. We propose a framework to jointly train a GFlowNet with an energy function, so that the GFlowNet learns to sample from the energy distribution, while the energy learns with an approximate MLE objective with negative samples from the GFlowNet. We demonstrate EB-GFN's effectiveness on various probabilistic modeling tasks. Code is publicly available at https://github.com/zdhNarsil/EB_GFN.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). Builds on 33 of its 61 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

33 of 61 references.

References · 33

  1. 2016Layer Normalizationcited by 5,579
  2. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  3. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  4. 2016Pixel Recurrent Neural Networkscited by 814
  5. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  6. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  7. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  8. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  9. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  10. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  11. 2021GFlowNet Foundationscited by 286
  12. 2021How to Train Your Energy-Based Modelscited by 271
21 more
  1. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  2. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  3. 2016A Theory of Generative ConvNetcited by 174
  4. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 147
  5. 2015A Complete Recipe for Stochastic Gradient MCMCcited by 146
  6. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 127
  7. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  8. 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
  9. 2016Neural Autoregressive Distribution Estimationcited by 94
  10. 2021Oops I Took A Gradient: Scalable Sampling for Discrete Distributionscited by 92
  11. 2020Generalized Energy Based Modelscited by 73
  12. 2020No MCMC for me: Amortized sampling for fast and stable training of energy-based modelscited by 64
  13. 2020Interference and Generalization in Temporal Difference Learningcited by 41
  14. 2019Exponential Family Estimation via Adversarial Dynamics Embeddingcited by 30
  15. 2020Training Deep Energy-Based Models with f-Divergence Minimizationcited by 29
  16. 2020Learning Discrete Energy-based Models via Auxiliary-variable Local Explorationcited by 29
  17. 2021Improved Autoregressive Modeling with Distribution Smoothingcited by 18
  18. 2015The Hamming Ball Samplercited by 16
  19. 2020Stein Variational Inference for Discrete Distributionscited by 16
  20. 2021Discovering Non-monotonic Autoregressive Orderings with Variational Inferencecited by 15
  21. 2019Sequence Modeling with Unconstrained Generation Ordercited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 18; 2023: 34; 2024: 28; 2025: 20; 2026: 13.

113 papers.

Sort:

By area:

  1. 2022Biological Sequence Design with GFlowNetscited by 172
  2. 2022Score-based Continuous-time Discrete Diffusion Modelscited by 167
  3. 2022Concrete Score Matching: Generalized Score Matching for Discrete Datacited by 144
  4. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 129
  5. 2022GFlowNets and variational inferencecited by 103
  6. 2023A theory of continuous generative flow networkscited by 98
  7. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  8. 2023Towards Understanding and Improving GFlowNet Trainingcited by 74
  9. 2023Robust Scheduling with GFlowNetscited by 67
  10. 2022Training and Inference on Any-Order Autoregressive Models the Right Waycited by 64
  11. 2023Generative Flow Networks as Entropy-Regularized RLcited by 60
  12. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
38 more
  1. 2024Ant Colony Sampling with GFlowNets for Combinatorial Optimizationcited by 53
  2. 2022Generative Augmented Flow Networkscited by 48
  3. 2023Sample-efficient Multi-objective Molecular Optimization with GFlowNetscited by 48
  4. 2024Improved off-policy training of diffusion samplerscited by 47
  5. 2023Local Search GFlowNetscited by 45
  6. 2022A Langevin-like Sampler for Discrete Distributionscited by 42
  7. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  8. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  9. 2024Discrete Probabilistic Inference as Control in Multi-path Environmentscited by 40
  10. 2022A Variational Perspective on Generative Flow Networkscited by 39
  11. 2025FlowRL: Matching Reward Distributions for LLM Reasoningcited by 38
  12. 2023Stochastic Generative Flow Networkscited by 32
  13. 2023Thompson sampling for improved exploration in GFlowNetscited by 31
  14. 2022Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayescited by 30
  15. 2023Maximum entropy GFlowNets with soft Q-learningcited by 30
  16. 2024Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetscited by 30
  17. 2023Distributional GFlowNets with Quantile Flowscited by 28
  18. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  19. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  20. 2023Learning to Scale Logits for Temperature-Conditional GFlowNetscited by 26
  21. 2022Unifying Generative Models with GFlowNets and Beyondcited by 24
  22. 2024Adaptive teachers for amortized samplerscited by 23
  23. 2022GFlowOut: Dropout with Generative Flow Networkscited by 22
  24. 2022Neuro-Symbolic Causal Reasoning Meets Signaling Game for Emergent Semantic Communicationscited by 20
  25. 2023PhyloGFN: Phylogenetic inference with generative flow networkscited by 20
  26. 2023CFlowNets: Continuous Control with Generative Flow Networkscited by 19
  27. 2025Learning to Sample Effective and Diverse Prompts for Text-to-Image Generationcited by 16
  28. 2023Improving Gradient-guided Nested Sampling for Posterior Inferencecited by 14
  29. 2025Generative Models in Decision Making: A Surveycited by 14
  30. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 14
  31. 2025Value Gradient Guidance for Flow Matching Alignmentcited by 14
  32. 2022Latent State Marginalization as a Low-cost Approach for Improving Explorationcited by 13
  33. 2024Pessimistic Backward Policy for GFlowNetscited by 13
  34. 2025Discrete Neural Flow Samplers with Locally Equivariant Transformercited by 13
  35. 2023Formulating Discrete Probability Flow Through Optimal Transportcited by 12
  36. 2024Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximizationcited by 12
  37. 2025Action Tokenizer Matters in In-Context Imitation Learningcited by 12
  38. 2022GFlowCausal: Generative Flow Networks for Causal Discoverycited by 11

50 most cited of 113 All 113 (JSON)