mlsanityData to 7 Oct 2026

Unifying Generative Models with GFlowNets and Beyond

arXiv 2209.02606 ↗First posted 6 Sep 2022cs.LG cs.AI stat.MLcited by 24

Not on the map. Why?

Abstract (arXiv)

There are many frameworks for deep generative modeling, each often presented with their own specific training algorithms and inference methods. Here, we demonstrate the connections between existing deep generative models and the recently introduced GFlowNet framework, a probabilistic inference machine which treats sampling as a decision-making process. This analysis sheds light on their overlapping traits and provides a unifying viewpoint through the lens of learning with Markovian trajectories. Our framework provides a means for unifying training and inference algorithms, and provides a route to shine a unifying light over many generative models. Beyond this, we provide a practical and experimentally verified recipe for improving generative modeling with insights from the GFlowNet perspective.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 35 of its 71 references that are in the map. First posted on arXiv 6 Sep 2022.

Builds on

35 of 71 references.

References · 35

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  8. 2021Variational Diffusion Modelscited by 1,145
  9. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  10. 2016Pixel Recurrent Neural Networkscited by 814
  11. 2017Deep Reinforcement Learning that Matterscited by 727
  12. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
23 more
  1. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  2. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  3. 2017Non-Autoregressive Neural Machine Translationcited by 457
  4. 2015Importance Weighted Autoencoderscited by 454
  5. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  6. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  7. 2016Ladder Variational Autoencoderscited by 315
  8. 2013A survey of the Schr"odinger problem and some of its connections with optimal transportcited by 286
  9. 2021GFlowNet Foundationscited by 286
  10. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  11. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
  12. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  13. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matchingcited by 182
  14. 2022Biological Sequence Design with GFlowNetscited by 172
  15. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 168
  16. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  17. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  18. 2015Hierarchical Variational Modelscited by 89
  19. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  20. 2022Conditional Simulation Using Diffusion Schr"odinger Bridgescited by 58
  21. 2020Learning Discrete Energy-based Models via Auxiliary-variable Local Explorationcited by 29
  22. 2017On Unifying Deep Generative Modelscited by 15
  23. 2021Unifying Likelihood-free Inference with Black-box Optimization and Beyondcited by 10

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 12; 2024: 3; 2025: 2.

24 papers.

Sort:

By area:

  1. 2022GFlowNets and variational inferencecited by 103
  2. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  3. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
  4. 2023Generative Flow Networks as Entropy-Regularized RLcited by 60
  5. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  6. 2022Generative Augmented Flow Networkscited by 48
  7. 2022A Variational Perspective on Generative Flow Networkscited by 39
  8. 2023Stochastic Generative Flow Networkscited by 32
  9. 2023Distributional GFlowNets with Quantile Flowscited by 28
  10. 2023Compositional Sculpting of Iterative Generative Processescited by 26
  11. 2023Learning to Scale Logits for Temperature-Conditional GFlowNetscited by 26
  12. 2022GFlowOut: Dropout with Generative Flow Networkscited by 22
12 more
  1. 2023CFlowNets: Continuous Control with Generative Flow Networkscited by 19
  2. 2024QGFN: Controllable Greediness with Action Valuescited by 18
  3. 2023Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Designcited by 17
  4. 2025Generative Models in Decision Making: A Surveycited by 14
  5. 2022Latent State Marginalization as a Low-cost Approach for Improving Explorationcited by 13
  6. 2023Order-Preserving GFlowNetscited by 13
  7. 2024RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetscited by 10
  8. 2022A Mathematical Framework for Learning Probability Distributionscited by 7
  9. 2023Generative Marginalization Modelscited by 4
  10. 2025Ergodic Generative Flowscited by 2
  11. 2023Meta Generative Flow Networks with Personalization for Task-Specific Adaptationcited by 1
  12. 2024Effective Reward Specification in Deep Reinforcement Learningcited by 0