Saved in:
Bibliographic Details
Main Authors: Huang, Yang, Chen, Jingrun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.02267
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914527605424128
author Huang, Yang
Chen, Jingrun
author_facet Huang, Yang
Chen, Jingrun
contents We introduce a composition-weighted symbolic regression framework for interpretable prediction of materials properties directly from chemical composition. The method jointly learns analytical functional forms and task-dependent elemental weightings without predefined descriptors. By incorporating max/min operators, it naturally enforces constraints such as non-negative band gaps and bounded classification probabilities, unifying regression and classification tasks. Efficient search is achieved through a hybrid Monte Carlo tree search--genetic programming algorithm with gradient-based refinement and parallel computation. Benchmarks on MatBench tasks show competitive accuracy relative to state-of-the-art black-box models while yielding explicit analytical expressions. Applied to III--V semiconductor alloys, the model produces smooth composition-dependent trends and learned elemental weights with chemically meaningful periodic behavior. This framework provides a scalable and interpretable route for materials discovery and property screening.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02267
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Composition-Weighted Symbolic Regression for General-Purpose Property Prediction
Huang, Yang
Chen, Jingrun
Materials Science
Computational Physics
We introduce a composition-weighted symbolic regression framework for interpretable prediction of materials properties directly from chemical composition. The method jointly learns analytical functional forms and task-dependent elemental weightings without predefined descriptors. By incorporating max/min operators, it naturally enforces constraints such as non-negative band gaps and bounded classification probabilities, unifying regression and classification tasks. Efficient search is achieved through a hybrid Monte Carlo tree search--genetic programming algorithm with gradient-based refinement and parallel computation. Benchmarks on MatBench tasks show competitive accuracy relative to state-of-the-art black-box models while yielding explicit analytical expressions. Applied to III--V semiconductor alloys, the model produces smooth composition-dependent trends and learned elemental weights with chemically meaningful periodic behavior. This framework provides a scalable and interpretable route for materials discovery and property screening.
title Composition-Weighted Symbolic Regression for General-Purpose Property Prediction
topic Materials Science
Computational Physics
url https://arxiv.org/abs/2605.02267