用硅的模型加速锗的训练，数据少也能高精度模拟
Enhancing Machine Learning Potentials through Transfer Learning across Chemical Elements
- 用硅的预训练模型初始化锗的模型，提升训练效率
- 小数据下力预测更准，模拟更稳定，温度适应性更强
- 适合数据稀缺的元素建模，尤其对新元素开发有帮助
机器学习势（MLPs）可在计算成本低得多的情况下实现从头算精度的模拟。但其性能依赖于充足的数据集以确保在化学空间和热力学条件下的泛化能力。数据生成耗时费力，亟需应对数据稀缺的新方法。本文提出在化学相似元素间进行势能面的迁移学习，具体为利用硅的已训练模型来初始化并加速锗的模型训练。基于经典力场和从头算数据集，实验表明迁移学习在力预测上优于从零开始训练，带来更稳定的模拟和更好的温度可迁移性。随着训练数据量减少，优势更加显著。跨目标性质分析显示，迁移学习虽有益处，但有时也会产生不利影响。结果表明，在数据稀缺场景下，元素间的迁移学习是构建高精度、数值稳定机器学习势的有效策略。
原文摘要 · Abstract (English)
Machine Learning Potentials (MLPs) can enable simulations of ab initio accuracy at orders of magnitude lower computational cost. However, their effectiveness hinges on the availability of considerable datasets to ensure robust generalization across chemical space and thermodynamic conditions. The generation of such datasets can be labor-intensive, highlighting the need for innovative methods to train MLPs in data-scarce scenarios. Here, we introduce transfer learning of potential energy surfaces between chemically similar elements. Specifically, we leverage the trained MLP for silicon to initialize and expedite the training of an MLP for germanium. Utilizing classical force field and ab initio datasets, we demonstrate that transfer learning surpasses traditional training from scratch in force prediction, leading to more stable simulations and improved temperature transferability. These advantages become even more pronounced as the training dataset size decreases. The out-of-target property analysis shows that transfer learning leads to beneficial but sometimes adversarial effects. Our findings demonstrate that transfer learning across chemical elements is a promising technique for developing accurate and numerically stable MLPs, particularly in a data-scarce regime.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。