Bifurcated Generative Flow Networks

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 efficie...

Full description

Saved in:
Bibliographic Details
Main Authors Li, Chunhui, Liu, Cheng-Hao, Liu, Dianbo, Cai, Qingpeng, Pan, Ling
Format Journal Article
LanguageEnglish
Published 03.06.2024
Subjects
Computer Science - Learning
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.48550/arxiv.2406.01901