Symmetry-Aware GFlowNets

• URL: http://arxiv.org/abs/2506.02685v1
• Date: Tue, 03 Jun 2025 09:38:15 GMT
• Title: Symmetry-Aware GFlowNets
• Authors: Hohyun Kim, Seunggeun Lee, Min-hwan Oh,
• Abstract summary: Generative Flow Networks (GFlowNets) offer a powerful framework for sampling graphs in proportion to their rewards.<n>Existing approaches suffer from systematic biases due to inaccuracies in state transition probability computations.<n>We introduce Symmetry-Aware GFlowNets (SA-GFN), a method that incorporates symmetry corrections into the learning process through reward scaling.
• Score: 7.196104022425989
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions [64.17845687013434]
  We propose ReDiSC, a structured diffusion model for structured node classification.<n>We show that ReDiSC achieves superior or highly competitive performance compared to state-of-the-art GNN, label propagation, and diffusion-based baselines.<n> Notably, ReDiSC scales effectively to large-scale datasets on which previous structured diffusion methods fail due to computational constraints.
  arXiv  Detail & Related papers  (2025-07-19T04:46:53Z)
• PNE-SGAN: Probabilistic NDT-Enhanced Semantic Graph Attention Network for LiDAR Loop Closure Detection [3.638946969851829]
  We introduce PNE-SGAN, a Probabilistic NDT-Enhanced Semantic Graph Attention Network.<n>PNE-SGAN enhances semantic graphs by using Normal Distributions Transform (NDT) covariance matrices as rich, discriminative geometric node features.<n>We demonstrate state-of-the-art performance, achieving Average Precision of 96.2% and 95.1%, respectively.
  arXiv  Detail & Related papers  (2025-04-11T06:25:11Z)
• Baking Symmetry into GFlowNets [58.932776403471635]
  GFlowNets have exhibited promising performance in generating diverse candidates with high rewards. This study aims to integrate symmetries into GFlowNets by identifying equivalent actions during the generation process.
  arXiv  Detail & Related papers  (2024-06-08T10:11:10Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Graph Out-of-Distribution Generalization with Controllable Data Augmentation [51.17476258673232]
  Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties. Due to the selection bias of training and testing data, distribution deviation is widespread. We propose OOD calibration to measure the distribution deviation of virtual samples.
  arXiv  Detail & Related papers  (2023-08-16T13:10:27Z)
• Stochastic Generative Flow Networks [89.34644133901647]
  Generative Flow Networks (or GFlowNets) learn to sample complex structures through the lens of "inference as control" Existing GFlowNets can be applied only to deterministic environments, and fail in more general tasks with dynamics. This paper introduces GFlowNets, a new algorithm that extends GFlowNets to environments.
  arXiv  Detail & Related papers  (2023-02-19T03:19:40Z)
• Learning GFlowNets from partial episodes for improved convergence and stability [56.99229746004125]
  Generative flow networks (GFlowNets) are algorithms for training a sequential sampler of discrete objects under an unnormalized target density. Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory. Inspired by the TD($lambda$) algorithm in reinforcement learning, we introduce subtrajectory balance or SubTB($lambda$), a GFlowNet training objective that can learn from partial action subsequences of varying lengths.
  arXiv  Detail & Related papers  (2022-09-26T15:44:24Z)
• FMP: Toward Fair Graph Message Passing against Topology Bias [43.70672256020857]
  A textsfFair textsfMessage textsfPassing (FMP) scheme is proposed to aggregate useful information from neighbors but minimize the effect of topology bias. The proposed FMP is effective, transparent, and compatible with back-propagation training.
  arXiv  Detail & Related papers  (2022-02-08T23:00:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.