Abstract:Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately simulate materials and molecules. Incorporating electronic structure information using multitask learning improves sample efficiency, however, training on full Hamiltonian matrices, which scale quadratically with the number of atoms, is intractable for large datasets. In this work, we show that multitask learning utilizing orbitally resolved semiempirical charges significantly improves sample efficiency and accuracy in MLIPs. To efficiently predict orbital charges, we implement a specialized equivariant model, reducing charge prediction error compared to an invariant baseline. By augmenting training with computationally inexpensive GFN1-xTB orbital charges, which scale linearly with the number of atoms, our model achieves a 46\% reduction in energy mean absolute error and requires five times less data to match the performance of energy-only models. Furthermore, our approach outperforms models trained on expensive density functional theory (DFT) atomic charges, capturing orbitally resolved electronic complexity and forcing the network to learn a physically accurate latent space that spontaneously clusters metals by shared chemical properties. Because orbital charges are only required during training, this approach preserves inference efficiency, providing a scalable recipe for developing accurate, data-efficient foundation models for complex chemical systems.
| Comments: | 16 pages, 6 figures |
| Subjects: | Chemical Physics (physics.chem-ph); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.24073 [physics.chem-ph] |
| (or arXiv:2605.24073v1 [physics.chem-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24073 arXiv-issued DOI via DataCite (pending registration) |
From: Ihor Neporozhnii [view email]
[v1]
Fri, 22 May 2026 14:12:27 UTC (6,158 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。