mlsanityData to 14 Oct 2026

Baking Symmetry into GFlowNets

arXiv 2406.05426 ↗First posted 8 Jun 2024cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

GFlowNets have exhibited promising performance in generating diverse candidates with high rewards. These networks generate objects incrementally and aim to learn a policy that assigns probability of sampling objects in proportion to rewards. However, the current training pipelines of GFlowNets do not consider the presence of isomorphic actions, which are actions resulting in symmetric or isomorphic states. This lack of symmetry increases the amount of samples required for training GFlowNets and can result in inefficient and potentially incorrect flow functions. As a consequence, the reward and diversity of the generated objects decrease. In this study, our objective is to integrate symmetries into GFlowNets by identifying equivalent actions during the generation process. Experimental results using synthetic data demonstrate the promising performance of our proposed approaches.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 8 Jun 2024.

Builds on

25 of 30 references.

References · 25

  1. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  2. 2021GFlowNet Foundationscited by 290
  3. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
  4. 2022Biological Sequence Design with GFlowNetscited by 174
  5. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 168
  6. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  7. 2019Relational Pooling for Graph Representationscited by 150
  8. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 114
  9. 2022GFlowNets and variational inferencecited by 106
  10. 2022Multi-Objective GFlowNetscited by 101
  11. 2018Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputscited by 98
  12. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 85
13 more
  1. 2023Robust Scheduling with GFlowNetscited by 69
  2. 2021ForceNet: A Graph Neural Network for Large-Scale Quantum Calculationscited by 58
  3. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  4. 2021Rotation Invariant Graph Neural Networks using Spin Convolutionscited by 52
  5. 2022Generative Augmented Flow Networkscited by 50
  6. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  7. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  8. 2023Stochastic Generative Flow Networkscited by 32
  9. 2023Distributional GFlowNets with Quantile Flowscited by 28
  10. 2023The Exact Sample Complexity Gain from Invariances for Kernel Regressioncited by 28
  11. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  12. 2022GFlowOut: Dropout with Generative Flow Networkscited by 22
  13. 2023Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embeddingcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025FlowRL: Matching Reward Distributions for LLM Reasoningcited by 40
  2. 2024Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examplescited by 30
  3. 2025Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewardscited by 11
  4. 2025Symmetry-Aware GFlowNetscited by 7
  5. 2026Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioningcited by 1
  6. 2025Planning-Augmented Sampling with Early Guidance for High-Reward Discoverycited by 0
  7. 2026Signal from Structure: Exploiting Submodular Upper Bounds in Generative Flow Networkscited by 0