Leveraging Legacy Data to Accelerate Materials Design via Preference Learning

Abstract

Machine learning applications in materials science are often hampered by shortage of experimental data. Integration with legacy data from past experiments is a viable way to solve the problem, but complex calibration is often necessary to use the data obtained under different conditions. In this paper, we present a novel calibration-free strategy to enhance the performance of Bayesian optimization with preference learning. The entire learning process is solely based on pairwise comparison of quantities (i.e., higher or lower) in the same dataset, and experimental design can be done without comparing quantities in different datasets. We demonstrate that Bayesian optimization is significantly enhanced via addition of legacy data for organic molecules and inorganic solid-state materials.

arXiv comment10 pages, 4 figures

References in corpus (5)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Big Data of Materials Science - Critical Role of the Descriptor
• Designing nanostructures for interfacial phonon transport via Bayesian optimization
• Bayesian machine learning for quantum molecular dynamics
• Bayesian optimization for the inverse scattering problem in quantum reaction dynamics