




















Abstract:In the rapidly advancing field of materials informatics, nonlinear machine learning models have demonstrated exceptional predictive capabilities for material properties. However, their black-box nature limits interpretability, and they may incorporate features that do not contribute to -- or even deteriorate -- model performance. This study employs explainable ML (XML) techniques, including permutation feature importance and the SHapley Additive exPlanation, applied to a pristine support vector regression model designed to predict band gaps at the GW level using 18 input features. Guided by XML-derived individual feature importance, a simple framework is proposed to construct reduced-feature predictive models. Model evaluations indicate that an XML-guided compact model, consisting of the top five features, achieves comparable accuracy to the pristine model on in-domain datasets (0.254 vs. 0.247 eV) while showing improved generalization with lower prediction errors on out-of-domain data (0.348 vs. 0.460 eV). Additionally, the study underscores the necessity for eliminating strongly correlated features (correlation coefficient greater than 0.8) to prevent misinterpretation and overestimation of feature importance before applying XML. This study highlights XML's effectiveness in developing simplified yet highly accurate machine learning models by clarifying feature roles, thereby reducing computational costs for feature acquisition and enhancing model trustworthiness for materials discovery.
| Comments: | 10 pages, 3 figures, SI is included, accpeted in Sci. Rep. (will be updated soon) |
| Subjects: | Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG) |
| Cite as: | arXiv:2503.04492 [cond-mat.mtrl-sci] |
| (or arXiv:2503.04492v3 [cond-mat.mtrl-sci] for this version) | |
| https://doi.org/10.48550/arXiv.2503.04492 arXiv-issued DOI via DataCite |
From: Joohwi Lee [view email]
[v1]
Thu, 6 Mar 2025 14:40:21 UTC (1,956 KB)
[v2]
Thu, 30 Oct 2025 03:24:21 UTC (4,833 KB)
[v3]
Thu, 23 Apr 2026 11:08:33 UTC (4,380 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。