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.

翻译：在药物发现和材料设计等领域，发现具有特定性质的新分子是一项关键挑战。基于深度学习的生成方法近期取得进展，但由于奖励函数评估的计算成本高昂，这些方法面临样本效率低下的问题。本文提出一种新颖的样本高效分子优化算法，通过GFlowNets训练（一种用于摊销推理的离策略方法）将强大的遗传算法知识蒸馏至深度生成策略中。该方法使深度生成策略能够学习已显式整合到遗传算法中的领域知识。我们的方法在官方分子优化基准测试中取得了最先进的性能，显著优于先前方法。该方法在针对SARS-CoV-2的抑制剂设计任务中也展现出卓越效果，且所需奖励函数调用次数大幅减少。