Genetic-guided GFlowNets for Sample Efficient Molecular Optimization

TL;DR

This paper introduces a genetic-guided GFlowNet approach for more sample-efficient molecular optimization, leveraging domain knowledge to outperform existing methods in drug discovery benchmarks.

Contribution

It presents a novel algorithm that distills genetic algorithms into GFlowNets, enhancing sample efficiency and integrating domain knowledge into molecular design.

Findings

Achieves state-of-the-art results in molecular optimization benchmarks.

Effectively designs SARS-CoV-2 inhibitors with fewer reward evaluations.

Outperforms previous methods significantly in sample efficiency.

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.