Baking Symmetry into GFlowNets
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929378545369088 |
|---|---|
| author | Ma, George Bengio, Emmanuel Bengio, Yoshua Zhang, Dinghuai |
| author_facet | Ma, George Bengio, Emmanuel Bengio, Yoshua Zhang, Dinghuai |
| contents | GFlowNets have exhibited promising performance in generating diverse candidates with high rewards. These networks generate objects incrementally and aim to learn a policy that assigns probability of sampling objects in proportion to rewards. However, the current training pipelines of GFlowNets do not consider the presence of isomorphic actions, which are actions resulting in symmetric or isomorphic states. This lack of symmetry increases the amount of samples required for training GFlowNets and can result in inefficient and potentially incorrect flow functions. As a consequence, the reward and diversity of the generated objects decrease. In this study, our objective is to integrate symmetries into GFlowNets by identifying equivalent actions during the generation process. Experimental results using synthetic data demonstrate the promising performance of our proposed approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05426 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Baking Symmetry into GFlowNets Ma, George Bengio, Emmanuel Bengio, Yoshua Zhang, Dinghuai Machine Learning GFlowNets have exhibited promising performance in generating diverse candidates with high rewards. These networks generate objects incrementally and aim to learn a policy that assigns probability of sampling objects in proportion to rewards. However, the current training pipelines of GFlowNets do not consider the presence of isomorphic actions, which are actions resulting in symmetric or isomorphic states. This lack of symmetry increases the amount of samples required for training GFlowNets and can result in inefficient and potentially incorrect flow functions. As a consequence, the reward and diversity of the generated objects decrease. In this study, our objective is to integrate symmetries into GFlowNets by identifying equivalent actions during the generation process. Experimental results using synthetic data demonstrate the promising performance of our proposed approaches. |
| title | Baking Symmetry into GFlowNets |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.05426 |