mlsanityData to 14 Oct 2026

Revisiting Non-Acyclic GFlowNets in Discrete Environments

arXiv 2502.07735 ↗First posted 11 Feb 2025cs.LG stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

Generative Flow Networks (GFlowNets) are a family of generative models that learn to sample objects from a given probability distribution, potentially known up to a normalizing constant. Instead of working in the object space, GFlowNets proceed by sampling trajectories in an appropriately constructed directed acyclic graph environment, greatly relying on the acyclicity of the graph. In our paper, we revisit the theory that relaxes the acyclicity assumption and present a simpler theoretical framework for non-acyclic GFlowNets in discrete environments. Moreover, we provide various novel theoretical insights related to training with fixed backward policies, the nature of flow functions, and connections between entropy-regularized RL and non-acyclic GFlowNets, which naturally generalize the respective concepts and theoretical results from the acyclic setting. In addition, we experimentally re-examine the concept of loss stability in non-acyclic GFlowNet training, as well as validate our own theoretical findings.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

35 of 43 references.

References · 35

  1. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  2. 2021GFlowNet Foundationscited by 290
  3. 2019A Theory of Regularized Markov Decision Processescited by 286
  4. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
  5. 2017A unified view of entropy-regularized Markov decision processescited by 182
  6. 2022Biological Sequence Design with GFlowNetscited by 174
  7. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  8. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 132
  9. 2022GFlowNets and variational inferencecited by 106
  10. 2023A theory of continuous generative flow networkscited by 101
  11. 2024Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Reviewcited by 98
  12. 2023Amortizing intractable inference in large language modelscited by 97
23 more
  1. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 85
  2. 2023Towards Understanding and Improving GFlowNet Trainingcited by 75
  3. 2024Amortizing intractable inference in diffusion models for vision, language, and controlcited by 72
  4. 2023Robust Scheduling with GFlowNetscited by 69
  5. 2023Generative Flow Networks as Entropy-Regularized RLcited by 64
  6. 2024Learning diverse attacks on large language models for robust red-teaming and safety tuningcited by 54
  7. 2024Ant Colony Sampling with GFlowNets for Combinatorial Optimizationcited by 53
  8. 2024Discrete Probabilistic Inference as Control in Multi-path Environmentscited by 44
  9. 2024RGFN: Synthesizable Molecular Generation Using GFlowNetscited by 41
  10. 2023Maximum entropy GFlowNets with soft Q-learningcited by 30
  11. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  12. 2024SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraintscited by 26
  13. 2023Learning Energy Decompositions for Partial Inference of GFlowNetscited by 24
  14. 2024QGFN: Controllable Greediness with Action Valuescited by 18
  15. 2024Pessimistic Backward Policy for GFlowNetscited by 14
  16. 2024Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximizationcited by 14
  17. 2024Improved Off-policy Reinforcement Learning in Biological Sequence Designcited by 13
  18. 2023A Theory of Non-Acyclic Generative Flow Networkscited by 12
  19. 2024Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networkscited by 11
  20. 2024Improving GFlowNets with Monte Carlo Tree Searchcited by 8
  21. 2024On Divergence Measures for Training GFlowNetscited by 6
  22. 2024Random Policy Evaluation Uncovers Policies of Generative Flow Networkscited by 5
  23. 2025Generative Flow Networks: Theory and Applications to Structure Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 6.

10 papers.

  1. 2025Adaptive Destruction Processes for Diffusion Samplerscited by 6
  2. 2025gfnx: Fast and Scalable Library for Generative Flow Networks in JAXcited by 3
  3. 2025Ergodic Generative Flowscited by 2
  4. 2026Learning Shortest Paths with Generative Flow Networkscited by 2
  5. 2025Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Trainingcited by 0
  6. 2026Your GFlowNet Secretly Learns an Optimal Transport Plancited by 0
  7. 2026Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernelscited by 0
  8. 2026Path-dependent Discrete Amortized Inferencecited by 0
  9. 2026Learning a Mixture of GFlowNetscited by 0
  10. 2026Towards Understanding the Training of GFlowNets: A Theoretical Perspectivecited by 0