BO-Muse: A human expert and AI teaming framework for accelerated experimental design

Bayesian Optimization (BO) (Shahriari et al., 2015) is a popular sample-efficient optimization technique to solve problems where the objective is expensive. It has been successfully applied in diverse areas (Greenhill et al., 2020) including material discovery (Li et al., 2017), alloy design (Barnett et al., 2020) and molecular design (Gómez-Bombarelli et al., 2018). However, standard BO typically operates tabula rasa, building its model of the objective from minimal priors that do not include domain-specific information. While there has been some progress made incorporating domain-specific knowledge to accelerate BO (Li et al., 2018; Hvarfner et al., 2022) or transfer learning from previous experiments (Shilton et al., 2017), it remains the case that there is a significant corpus of knowledge and expertise that could potentially accelerate BO even further but which remain largely untapped due to the inherent complexities involved in knowledge extraction and exploitation. In particular, this often arises from the fact that experts tend to organize their knowledge in complex schema containing concepts, attributes and relationships (Rousseau, 2001), making the elicitation of relevant expert knowledge, both quantitative and qualitative, a difficult task.