Genetic-guided GFlowNets for Sample Efficient Molecular Optimization

Hyeonah Kim, Minsu Kim, Sanghyeok Choi, Jinkyoo Park

Keywords: Molecular Optimization, Sample Efficiency, Generative Flow Networks, Genetic Algorithm

TL;DR: We propose a genetic-guided GFlowNet, which integrates a genetic search to guide GFlowNets to explore high-reward regions efficiently, achieving SOTA performance in an official molecular optimization benchmark.

Abstract: 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.

Primary Area: Machine learning for other sciences and fields

Submission Number: 4413