Generative Flow Networks (GFlowNets), a new family of probabilistic samplers,
have recently emerged as a promising framework for learning stochastic policies
that generate high-quality and diverse objects proportionally to their rewards.
However, existing GFlowNets often suffer from low data efficiency due to the
direct parameterization of edge flows or reliance on backward policies that may
struggle to scale up to large action spaces. In this paper, we introduce
Bifurcated GFlowNets (BN), a novel approach that employs a bifurcated
architecture to factorize the flows into separate representations for state
flows and edge-based flow allocation. This factorization enables BN to learn
more efficiently from data and better handle large-scale problems while
maintaining the convergence guarantee. Through extensive experiments on
standard evaluation benchmarks, we demonstrate that BN significantly improves
learning efficiency and effectiveness compared to strong baselines.

生成流网络（GFlowNets）是一种有前景的概率抽样框架，目前出现了一种新的家族。然而，现有的 GFlowNets 由于边缘流的直接参数化或依赖于可能难以扩展到大型操作空间的反向策略，往往导致数据效率较低。本文介绍了一种称为 Bifurcated GFlowNets（BN）的新方法，该方法采用分岔结构设计，将流程分解成状态流程和基于边缘的流程分配的独立表示。此分解使得 BN 能够更有效地从数据中学习，并更好地处理大规模问题，同时保持收敛保证。通过在标准评估基准上进行了大量实验，我们证明 BN 相对于强基准模型显著提高了学习效率和效果。