mlsanityData to 14 Oct 2026

Symmetry-Aware GFlowNets

arXiv 2506.02685 ↗First posted 3 Jun 2025stat.ML cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Generative Flow Networks (GFlowNets) offer a powerful framework for sampling graphs in proportion to their rewards. However, existing approaches suffer from systematic biases due to inaccuracies in state transition probability computations. These biases, rooted in the inherent symmetries of graphs, impact both atom-based and fragment-based generation schemes. To address this challenge, we introduce Symmetry-Aware GFlowNets (SA-GFN), a method that incorporates symmetry corrections into the learning process through reward scaling. By integrating bias correction directly into the reward structure, SA-GFN eliminates the need for explicit state transition computations. Empirical results show that SA-GFN enables unbiased sampling while enhancing diversity and consistently generating high-reward graphs that closely match the target distribution.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 29 of its 36 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

29 of 36 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  4. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 669
  5. 2019Graph Transformer Networkscited by 523
  6. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  7. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  8. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  9. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  10. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  11. 2021GFlowNet Foundationscited by 290
  12. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
17 more
  1. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 234
  2. 2018Learning Deep Generative Models of Graphscited by 229
  3. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
  4. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 132
  5. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 114
  6. 2022Multi-Objective GFlowNetscited by 101
  7. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 85
  8. 2023Autoregressive Diffusion Model for Graph Generationcited by 83
  9. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 82
  10. 2023Towards Understanding and Improving GFlowNet Trainingcited by 75
  11. 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
  12. 2023Generative Flow Networks as Entropy-Regularized RLcited by 64
  13. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  14. 2021Order Matters: Probabilistic Modeling of Node Sequence for Graph Generationcited by 33
  15. 2023Maximum entropy GFlowNets with soft Q-learningcited by 30
  16. 2025Learning-Order Autoregressive Models with Application to Molecular Graph Generationcited by 29
  17. 2024Baking Symmetry into GFlowNetscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Avoid What You Know: Divergent Trajectory Balance for GFlowNetscited by 4
  2. 2026Path-dependent Discrete Amortized Inferencecited by 0
  3. 2026Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Constructioncited by 0
  4. 2026Learning a Mixture of GFlowNetscited by 0
  5. 2026Beyond Action Entropy: Quotient-Space Exploration for Genome-Scale Metabolic Model Repaircited by 0
  6. 2026MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spacescited by 0
  7. 2026SNACK: A Sequential Notation Framework for Probabilistic Graph Generationcited by 0