Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916543981420544 |
|---|---|
| author | Kim, Hyeonah Kim, Minsu Choi, Sanghyeok Park, Jinkyoo |
| author_facet | Kim, Hyeonah Kim, Minsu Choi, Sanghyeok Park, Jinkyoo |
| contents | The challenge of discovering new molecules with desired properties is crucial in domains like drug discovery and material design. Recent advances in deep learning-based generative methods have shown promise but face the issue of sample efficiency due to the computational expense of evaluating the reward function. This paper proposes a novel algorithm for sample-efficient molecular optimization by distilling a powerful genetic algorithm into deep generative policy using GFlowNets training, the off-policy method for amortized inference. This approach enables the deep generative policy to learn from domain knowledge, which has been explicitly integrated into the genetic algorithm. Our method achieves state-of-the-art performance in the official molecular optimization benchmark, significantly outperforming previous methods. It also demonstrates effectiveness in designing inhibitors against SARS-CoV-2 with substantially fewer reward calls. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05961 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Genetic-guided GFlowNets for Sample Efficient Molecular Optimization Kim, Hyeonah Kim, Minsu Choi, Sanghyeok Park, Jinkyoo Biomolecules Machine Learning Neural and Evolutionary Computing The challenge of discovering new molecules with desired properties is crucial in domains like drug discovery and material design. Recent advances in deep learning-based generative methods have shown promise but face the issue of sample efficiency due to the computational expense of evaluating the reward function. This paper proposes a novel algorithm for sample-efficient molecular optimization by distilling a powerful genetic algorithm into deep generative policy using GFlowNets training, the off-policy method for amortized inference. This approach enables the deep generative policy to learn from domain knowledge, which has been explicitly integrated into the genetic algorithm. Our method achieves state-of-the-art performance in the official molecular optimization benchmark, significantly outperforming previous methods. It also demonstrates effectiveness in designing inhibitors against SARS-CoV-2 with substantially fewer reward calls. |
| title | Genetic-guided GFlowNets for Sample Efficient Molecular Optimization |
| topic | Biomolecules Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2402.05961 |