Representations and strategies for transferable machine learning improve model performance in chemical discovery
Name
5.0082964.pdf
Description
Published version
Size
5.65 MB
Format
Adobe PDF
Checksum (MD5)
54c9829ad7079270f393df529a4dd1f5
Author(s)
Harper, Daniel R
Nandy, Aditya
Arunachalam, Naveen
Duan, Chenru
Janet, Jon Paul
Kulik, Heather J
Date Issued
2022
Journal
The Journal of Chemical Physics
Publisher
AIP Publishing
Citation
Harper, Daniel R, Nandy, Aditya, Arunachalam, Naveen, Duan, Chenru, Janet, Jon Paul et al. 2022. "Representations and strategies for transferable machine learning improve model performance in chemical discovery." The Journal of Chemical Physics, 156 (7).
Version
Final published version
Abstract
Strategies for machine-learning(ML)-accelerated discovery that are general
across materials composition spaces are essential, but demonstrations of ML
have been primarily limited to narrow composition variations. By addressing the
scarcity of data in promising regions of chemical space for challenging targets
like open-shell transition-metal complexes, general representations and
transferable ML models that leverage known relationships in existing data will
accelerate discovery. Over a large set (ca. 1000) of isovalent transition-metal
complexes, we quantify evident relationships for different properties (i.e.,
spin-splitting and ligand dissociation) between rows of the periodic table
(i.e., 3d/4d metals and 2p/3p ligands). We demonstrate an extension to
graph-based revised autocorrelation (RAC) representation (i.e., eRAC) that
incorporates the effective nuclear charge alongside the nuclear charge
heuristic that otherwise overestimates dissimilarity of isovalent complexes. To
address the common challenge of discovery in a new space where data is limited,
we introduce a transfer learning approach in which we seed models trained on a
large amount of data from one row of the periodic table with a small number of
data points from the additional row. We demonstrate the synergistic value of
the eRACs alongside this transfer learning strategy to consistently improve
model performance. Analysis of these models highlights how the approach
succeeds by reordering the distances between complexes to be more consistent
with the periodic table, a property we expect to be broadly useful for other
materials domains.
MIT Department
Massachusetts Institute of Technology. Department of Chemistry
Massachusetts Institute of Technology. Department of Chemical Engineering
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1063/5.0082964
