Exploring Multiple High-Scoring Subspaces in Generative Flow Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917269867593728 |
|---|---|
| author | Yu, Xuan Wang, Xu Zhu, Rui Zhang, Yudong Wang, Yang |
| author_facet | Yu, Xuan Wang, Xu Zhu, Rui Zhang, Yudong Wang, Yang |
| contents | As a probabilistic sampling framework, Generative Flow Networks (GFlowNets) show strong potential for constructing complex combinatorial objects through the sequential composition of elementary components. However, existing GFlowNets often suffer from excessive exploration over vast state spaces, leading to over-sampling of low-reward regions and convergence to suboptimal distributions. Effectively biasing GFlowNets toward high-reward solutions remains a non-trivial challenge. In this paper, we propose CMAB-GFN, which integrates a combinatorial multi-armed bandit (CMAB) framework with GFlowNet policies. The CMAB component prunes low-quality actions, yielding compact high-scoring subspaces for exploration. Restricting GFNs to these compact high-scoring subspaces accelerates the discovery of high-value candidates, while the exploration of different subspaces ensures that diversity is not sacrificed. Experimental results on multiple tasks demonstrate that CMAB-GFN generates higher-reward candidates than existing approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11491 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploring Multiple High-Scoring Subspaces in Generative Flow Networks Yu, Xuan Wang, Xu Zhu, Rui Zhang, Yudong Wang, Yang Machine Learning As a probabilistic sampling framework, Generative Flow Networks (GFlowNets) show strong potential for constructing complex combinatorial objects through the sequential composition of elementary components. However, existing GFlowNets often suffer from excessive exploration over vast state spaces, leading to over-sampling of low-reward regions and convergence to suboptimal distributions. Effectively biasing GFlowNets toward high-reward solutions remains a non-trivial challenge. In this paper, we propose CMAB-GFN, which integrates a combinatorial multi-armed bandit (CMAB) framework with GFlowNet policies. The CMAB component prunes low-quality actions, yielding compact high-scoring subspaces for exploration. Restricting GFNs to these compact high-scoring subspaces accelerates the discovery of high-value candidates, while the exploration of different subspaces ensures that diversity is not sacrificed. Experimental results on multiple tasks demonstrate that CMAB-GFN generates higher-reward candidates than existing approaches. |
| title | Exploring Multiple High-Scoring Subspaces in Generative Flow Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.11491 |