Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. Robustness of Local Predictions in Atomistic Machine Learning Models
 
Loading...
Thumbnail Image
research article

Robustness of Local Predictions in Atomistic Machine Learning Models

Chong, Sanggyu  
•
Grasselli, Federico  
•
Ben Mahmoud, Chiheb  
Show more
November 10, 2023
Journal of Chemical Theory and Computation

Machine learning (ML) models for molecules and materials commonly rely on a decomposition of the global target quantity into local, atom-centered contributions. This approach is convenient from a computational perspective, enabling large-scale ML-driven simulations with a linear-scaling cost and also allows for the identification and posthoc interpretation of contributions from individual chemical environments and motifs to complicated macroscopic properties. However, even though practical justifications exist for the local decomposition, only the global quantity is rigorously defined. Thus, when the atom-centered contributions are used, their sensitivity to the training strategy or the model architecture should be carefully considered. To this end, we introduce a quantitative metric, which we call the local prediction rigidity (LPR), that allows one to assess how robust the locally decomposed predictions of ML models are. We investigate the dependence of the LPR on the aspects of model training, particularly the composition of training data set, for a range of different problems from simple toy models to real chemical systems. We present strategies to systematically enhance the LPR, which can be used to improve the robustness, interpretability, and transferability of atomistic ML models.

  • Details
  • Metrics
Type
research article
DOI
10.1021/acs.jctc.3c00704
Web of Science ID

WOS:001110584800001

Author(s)
Chong, Sanggyu  
•
Grasselli, Federico  
•
Ben Mahmoud, Chiheb  
•
Morrow, Joe D.
•
Deringer, Volker L.
•
Ceriotti, Michele  
Date Issued

2023-11-10

Publisher

Amer Chemical Soc

Published in
Journal of Chemical Theory and Computation
Volume

19

Issue

22

Start page

8020

End page

8031

Subjects

Physical Sciences

•

Electronic-Structure Calculations

•

Expansion Methods

•

Density

Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
COSMO  
FunderGrant Number

H2020 European Research Council

101001890-FIAMMA

European Research Council (ERC) under the European Union

101018557

European Union

EP/S023828/1

Show more
Available on Infoscience
February 20, 2024
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/204456
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés