Abstract:Machine learning (ML) models for electronic structure typically rely on large datasets generated by computationally expensive Kohn-Sham density functional theory calculations, as it is not known a priori which portions of the data are essential for accurate learning. Here, we reveal significant redundancies in electronic structure datasets across diverse material systems and attribute them to the low intrinsic dimensionality of the underlying data. We show that even random pruning can substantially reduce dataset size with minimal degradation in predictive accuracy. Moreover, a state-of-the-art coverage-based pruning strategy that samples data across all learning difficulties preserves chemical accuracy and model generalizability while using up to two orders of magnitude less data and reducing training time by a factor of three or more. We further demonstrate that the essential electronic structure information lies on a low-dimensional, non-linear manifold, providing a geometric explanation for the observed prunability. These observations are consistent with the predominance of local atomic environments in determining electronic properties, as suggested by nearsightedness arguments, and indicate that large-scale datasets may contain highly overlapping information. Our findings challenge the prevailing assumption that such extensive datasets are necessary for accurate ML-based electronic structure predictions and open a path toward identifying minimal, representative datasets for each material class.
| Subjects: | Materials Science (cond-mat.mtrl-sci); Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (cs.LG); Computational Physics (physics.comp-ph); Quantum Physics (quant-ph) |
| Cite as: | arXiv:2507.09001 [cond-mat.mtrl-sci] |
| (or arXiv:2507.09001v3 [cond-mat.mtrl-sci] for this version) | |
| https://doi.org/10.48550/arXiv.2507.09001 arXiv-issued DOI via DataCite |
From: Susanta Ghosh [view email]
[v1]
Fri, 11 Jul 2025 20:08:07 UTC (16,979 KB)
[v2]
Tue, 23 Dec 2025 02:45:24 UTC (19,004 KB)
[v3]
Fri, 1 May 2026 03:34:46 UTC (18,669 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。