Many crucial scientific problems involve designing novel molecules with desired properties, which can be formulated as a black-box optimization problem over the discrete chemical space. In practice, multiple conflicting objectives and costly evaluations (e.g., wet-lab experiments) make the diversity of candidates paramount. Computational methods have achieved initial success but still struggle with considering diversity in both objective and search space. To fill this gap, we propose a multi-objective Bayesian optimization (MOBO) algorithm leveraging the hypernetwork-based GFlowNets (HN-GFN) as an acquisition function optimizer, with the purpose of sampling a diverse batch of candidate molecular graphs from an approximate Pareto front. Using a single preference-conditioned hypernetwork, HN-GFN learns to explore various trade-offs between objectives. We further propose a hindsight-like off-policy strategy to share high-performing molecules among different preferences in order to speed up learning for HN-GFN. We empirically illustrate that HN-GFN has adequate capacity to generalize over preferences. Moreover, experiments in various real-world MOBO settings demonstrate that our framework predominantly outperforms existing methods in terms of candidate quality and sample efficiency. The code is available at https://github.com/violet-sto/HN-GFN.

翻译：许多关键科学问题涉及设计具有所需性质的新型分子，这可以形式化为离散化学空间上的黑箱优化问题。实际应用中，多个相互冲突的目标和高昂的评估成本（如湿实验）使得候选分子的多样性至关重要。计算方法已取得初步成功，但在目标空间和搜索空间中兼顾多样性方面仍面临挑战。为填补这一空白，我们提出一种基于超网络的GFlowNets（HN-GFN）作为采集函数优化器的多目标贝叶斯优化（MOBO）算法，旨在从近似帕累托前沿中采样多样化的候选分子图批次。通过单个偏好条件超网络，HN-GFN学习探索目标间的不同权衡。我们进一步提出类似后见之明的离策略方法，在不同偏好间共享高性能分子，以加速HN-GFN的学习。实验表明HN-GFN具有充分的偏好泛化能力。此外，在多种真实世界MOBO场景中的实验证明，我们的框架在候选质量和样本效率方面均显著优于现有方法。代码开源地址：https://github.com/violet-sto/HN-GFN。