Auto-MatRegressor: liberating machine learning alchemists
No Thumbnail Available
Date
2023-06-30
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Abstract
Machine learning (ML) is widely used to uncover structure–property relationships of materials due to its ability to quickly find potential data patterns and make accurate predictions. However, like alchemists, materials scientists are plagued by time-consuming and labor-intensive experiments to build high-accuracy ML models. Here, we propose an automatic modeling method based on meta-learning for materials property prediction named Auto-MatRegressor, which automates algorithm selection and hyperparameter optimization by learning from previous modeling experience, i.e., meta-data on historical datasets. The meta-data used in this work consists of 27 meta-features that characterize the datasets and the prediction performances of 18 algorithms commonly used in materials science. To recommend optimal algorithms, a collaborative meta-learning method embedded with domain knowledge quantified by a materials categories tree is designed. Experiments on 60 datasets show that compared with the traditional modeling method from scratch, Auto-MatRegressor automatically selects appropriate algorithms at lower computational cost, which accelerates constructing ML models with good prediction accuracy. Auto-MatRegressor supports dynamic expansion of meta-data with the increase of the number of materials datasets and other required algorithms and can be applied to any ML materials discovery and design task. © 2023 Science China Press. Published by Elsevier B.V. and Science China Press. All rights reserved.
Description
Keywords
Machine Learning, Materials testing, Datasets, Algorithms, Automation, Prediction equations, Materials
Citation
Liu, Y., Wang, S., Yang, Z., Avdeev, M., & Shi, S. (2023). Auto-MatRegressor: liberating machine learning alchemists. Science Bulletin, 68(12), 1259-1270. doi.:10.1016/j.scib.2023.05.017