DeepAI AI Chat
Log In Sign Up

Leveraging Legacy Data to Accelerate Materials Design via Preference Learning

by   Xiaolin Sun, et al.

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.


page 7

page 9

page 10


Bayesian Optimization in Materials Science: A Survey

Bayesian optimization is used in many areas of AI for the optimization o...

Lifelong Bayesian Optimization

Automatic Machine Learning (Auto-ML) systems tackle the problem of autom...

Multi-objective simulation optimization of the adhesive bonding process of materials

Automotive companies are increasingly looking for ways to make their pro...

Optimal measurement network of pairwise differences

When both the difference between two quantities and their individual val...

Machine-Learning-Optimized Perovskite Nanoplatelet Synthesis

With the demand for renewable energy and efficient devices rapidly incre...