mlsanityData to 14 Oct 2026

A Theory of Non-Acyclic Generative Flow Networks

arXiv 2312.15246 ↗First posted 23 Dec 2023cs.LG cs.AI cs.NAcited by 12

Not on the map. Why?

Abstract (arXiv)

GFlowNets is a novel flow-based method for learning a stochastic policy to generate objects via a sequence of actions and with probability proportional to a given positive reward. We contribute to relaxing hypotheses limiting the application range of GFlowNets, in particular: acyclicity (or lack thereof). To this end, we extend the theory of GFlowNets on measurable spaces which includes continuous state spaces without cycle restrictions, and provide a generalization of cycles in this generalized context. We show that losses used so far push flows to get stuck into cycles and we define a family of losses solving this issue. Experiments on graphs and continuous tasks validate those principles.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 13 of its 26 references that are in the map. First posted on arXiv 23 Dec 2023.

Builds on

13 of 26 references.

References · 13

  1. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  2. 2020A Generalization of Transformer Networks to Graphscited by 661
  3. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  4. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
  5. 2023A theory of continuous generative flow networkscited by 101
  6. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  7. 2021Local-Global MCMC kernels: the best of both worldscited by 22
  8. 2018A Framework for Adaptive MCMC Targeting Multimodal Distributionscited by 21
  9. 2023CFlowNets: Continuous Control with Generative Flow Networkscited by 19
  10. 2023Generative Flow Networks: a Markov Chain Perspectivecited by 14
  11. 2022Neural Topological Ordering for Computation Graphscited by 12
  12. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
1 more
  1. 2023Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 5.

12 papers.

  1. 2025Generative Models in Decision Making: A Surveycited by 15
  2. 2024Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networkscited by 11
  3. 2025Revisiting Non-Acyclic GFlowNets in Discrete Environmentscited by 10
  4. 2025Adaptive Destruction Processes for Diffusion Samplerscited by 6
  5. 2025gfnx: Fast and Scalable Library for Generative Flow Networks in JAXcited by 3
  6. 2025Ergodic Generative Flowscited by 2
  7. 2026Learning Shortest Paths with Generative Flow Networkscited by 2
  8. 2025Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Trainingcited by 0
  9. 2026WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptationcited by 0
  10. 2026Your GFlowNet Secretly Learns an Optimal Transport Plancited by 0
  11. 2026Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernelscited by 0
  12. 2026Path-dependent Discrete Amortized Inferencecited by 0