Materials representations organize transferable supervision for chemical extrapolation

Materials discovery often requires chemical extrapolation beyond labeled data. When target compounds contain elements absent from training, which compounds of other elements provide transferable supervision remains unclear. Here we show that, without target-property labels, materials representations rank other elements by the supervision their compounds provide. Engineered descriptors rank them largely by elemental-property similarity, whereas a pretrained crystal-graph encoder ranks them by the geometry of its learned representation. At fixed training-set size, excluding the compounds of the encoder's six top-ranked elements raises formation-energy and bandgap errors by 100-110 meV per atom and 42-85 meV, versus little change for six lower-ranked elements. The rankings hold across properties, regressors and datasets. The encoder's ranking outperforms elemental-property similarity and periodic groups, suggesting that it captures how elements behave within compounds. Materials representations thus organize transferable supervision, which can be identified before model training, informing dataset assessment and label acquisition.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23837
Primary Topic
Machine Learning in Materials Science
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Materials representations organize transferable supervision for chemical extrapolation

Enda Xiao, Terumasa Tadano
arXiv (Cornell University)
Machine Learning in Materials Science
preprint

Materials representations organize transferable supervision for chemical extrapolation

Enda Xiao, Terumasa Tadano
preprint en

Abstract

Materials discovery often requires chemical extrapolation beyond labeled data. When target compounds contain elements absent from training, which compounds of other elements provide transferable supervision remains unclear. Here we show that, without target-property labels, materials representations rank other elements by the supervision their compounds provide. Engineered descriptors rank them largely by elemental-property similarity, whereas a pretrained crystal-graph encoder ranks them by the geometry of its learned representation. At fixed training-set size, excluding the compounds of the encoder's six top-ranked elements raises formation-energy and bandgap errors by 100-110 meV per atom and 42-85 meV, versus little change for six lower-ranked elements. The rankings hold across properties, regressors and datasets. The encoder's ranking outperforms elemental-property similarity and periodic groups, suggesting that it captures how elements behave within compounds. Materials representations thus organize transferable supervision, which can be identified before model training, informing dataset assessment and label acquisition.

arXiv (Cornell University)
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon