LI, K.
, DeCost, B.
, Choudhary, K.
, Greenwood, M.
and Hattrick-Simpers, J.
(2023),
A critical examination of robustness and generalizability of machine learning prediction of materials properties, npj Computational Materials, [online], https://doi.org/10.1038/s41524-023-01012-9, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=935648
(Accessed April 27, 2024)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
A critical examination of robustness and generalizability of machine learning prediction of materials properties
Published
Author(s)
Kangming LI, , , Michael Greenwood, Jason Hattrick-Simpers
Abstract
Recent advances in machine learning (ML) have led to substantial performance improvement in material database benchmarks, but an excellent benchmark score may not imply good generalization performance. Here we show that ML models trained on Materials Project 2018 can have severely degraded performance on new compounds in Materials Project 2021 due to the distribution shift. We discuss how to foresee the issue with a few simple tools. Firstly, the uniform manifold approximation and projection (UMAP) can be used to investigate the relation between the training and test data within the feature space. Secondly, the disagreement between multiple ML models on the test data can illuminate out-of-distribution samples. We demonstrate that the UMAP-guided and query by committee acquisition strategies can greatly improve prediction accuracy by adding only 1 % of the test data. We believe this work provides valuable insights for building databases and models that enable better robustness and generalizability.Citation
npj Computational Materials
Pub Type
Journals
Download Paper
Keywords
DFT, Machine Learning
Citation
Created April 7, 2023, Updated April 10, 2023