Sanggyu Chong^1*, Federico Grasselli¹, Chiheb Ben Mahmoud¹, Joe Morrow², Volker Deringer², Michele Ceriotti¹

1 Laboratory of Computational Science and Modeling (COSMO), IMX, École Polytechnique Fédérale de Lausanne (EPFL), 1015 Lausanne, Switzerland

2 Department of Chemistry, Inorganic Chemistry Laboratory, University of Oxford, Oxford OX1 3QR, United Kingdom

* Corresponding authors emails: sanggyu.chong@epfl.ch

DOI10.24435/materialscloud:re-0d [version v1]

Publication date: Jun 30, 2023

How to cite this record

Sanggyu Chong, Federico Grasselli, Chiheb Ben Mahmoud, Joe Morrow, Volker Deringer, Michele Ceriotti, Robustness of local predictions in atomistic machine learning models, Materials Cloud Archive 2023.102 (2023), doi: 10.24435/materialscloud:re-0d.

Description

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 can also be used to deduce useful structure--property relations as they associate simple atomic motifs with complicated macroscopic properties. However, even though there exist practical justifications for these decompositions, only the global quantity is rigorously defined, and thus it is unclear to what extent the atomistic terms predicted by the model can be trusted. Here, we introduce a quantitative metric, which we call the local prediction rigidity (LPR), to assess how robust the locally decomposed predictions of ML models are. We investigate the dependence of LPR on the details of model training, e.g. composition of the dataset, for several different problems ranging 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 the resulting atomistic ML models. This repository contains datasets and Jupyter notebooks employed to corroborate the results of the above study.

Materials Cloud sections using this data

Files

File name	Size	Description
LPR_supp_notebook_dataset.tar.gz MD5md5:68664f36b80f27317378e76fa62a6406	12.9 MiB	tar file containing datasets and notebooks
README.txt MD5md5:a0331a12aa07fc5269de7ccb738c8a13	1.8 KiB	README file containing instructions to run the notebooks correctly

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Keywords

Marie Curie Fellowship ERC EPSRC