多保真度训练如何重塑原子模型的不确定性分解
Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models
AI 导读
一项 arXiv 研究考察多保真度训练对原子模型预测不确定性的影响，使用在 ANI-1x 上训练的 mean-variance MACE 模型深度集成，对比高保真从头训练与低保真预训练加微调两种方案。
正文 · 原文
Abstract:Multi-fidelity training, which combines abundant low-fidelity data with scarce high-fidelity labels, is increasingly common in atomistic modeling, but its effect on predictive uncertainty remains largely unexplored. We investigate this question using deep ensembles of mean-variance MACE models trained on ANI-1x, contrasting high-fidelity training from scratch with low-fidelity pretraining followed by fine-tuning. We characterize aleatoric, epistemic, and total uncertainty throughout training and under two distribution shifts: unseen molecular systems and higher-energy configurations. We find that pretraining reduces prediction error and improves uncertainty-based ranking across all test sets, but does not yield well-calibrated predictive variances; calibration deteriorates more severely under energy extrapolation. Training-dynamics analysis localizes most of this calibration degradation to high-fidelity optimization, during which the learned aleatoric variance becomes overconfident on held-out data. Moreover, multi-fidelity fine-tuning produces a more effective uncertainty-based acquisition function than high-fidelity training from scratch. These findings show that uncertainty ranking and calibration capture distinct properties and must be assessed separately in multi-fidelity atomistic models, especially under extrapolation.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35560 [cs.LG] |
| (or arXiv:2610.35560v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35560 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Matteo Tolloso [view email]
[v1]
Mon, 26 Oct 2026 15:01:42 UTC (1,359 KB)
来源：arXiv cs.AI · arxiv.org