Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning
cs.LG
Submitted: 2026-02-12
Updated: 2026-09-10
License: http://creativecommons.org/licenses/by/4.0/
The gist: Generative Flow Networks (GFlowNets) have shown promising potential to generate high-scoring candidates with probability proportional to their rewards.
Terminology
Abstract
Generative Flow Networks (GFlowNets) have shown promising potential to generate high-scoring candidates with probability proportional to their rewards. As existing GFlowNets freely explore in state space, they encounter significant convergence challenges when scaling to large state spaces. Addressing this issue, this paper proposes to restrict the exploration of actor. A planner is introduced to partition the entire state space into overlapping partial state spaces. Given their limited size, these partial state spaces allow the actor to efficiently identify subregions with higher rewards. A heuristic strategy is introduced to switch partial regions thus preventing the actor from wasting time exploring fully explored or low-reward partial regions. By iteratively exploring these partial state spaces, the actor learns to converge towards the high-reward subregions within the entire state space. Experiments on several widely used datasets demonstrate that converges faster than existing works on large state spaces. Furthermore, not only generates candidates with higher rewards but also significantly improves their diversity.
Sources
- Local Search GFlowNets
- Baking Symmetry into GFlowNets
- Pre-Training and Fine-Tuning Generative Flow Networks
- Generative Augmented Flow Networks
- Proximal Policy Optimization Algorithms
- AdaLead: A simple and robust adaptive greedy search algorithm for sequence design
- MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
- On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces
- Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
- Unifying Generative Models with GFlowNets and Beyond
- Distributional GFlowNets with Quantile Flows
- A Variational Perspective on Generative Flow Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks