用迁移学习提升材料热导率预测精度，小数据也能有好效果。
Transfer Learning for Deep Learning-based Prediction of Lattice Thermal Conductivity
- 先在大量低精度数据上预训练，再用小规模高精度数据微调。
- 模型在仅有几十种材料的有限数据下仍显著提升预测准确率。
- 适合材料基因组研究者，尤其关注热导率低的新型材料设计。
机器学习有望通过从原子级描述符或结构高通量预测理想宏观性质，加速材料发现。然而，精确性质数据稀缺是主要障碍，导致预测模型精度和泛化能力受限。以晶格热导率（LTC）为例，现有基于第一性原理（DFT）计算的精确数据集仅包含数十种材料，且多样性不足。本文基于此，研究迁移学习对深度学习模型（ParAIsite）精度与泛化能力的影响。以现有MEGNet模型为基础，发现通过在不同任务上微调预训练模型可获得性能提升；更关键的是，先在大规模低质量近似数据集（基于AGL模型）上微调，再在小规模高质量数据集上进行二次微调，可实现更大程度的性能跃升。该方法为探索大规模数据库以寻找低热导率材料提供了新路径，并为高质量数据稀缺领域的精准预测开辟了可能性。
原文摘要 · Abstract (English)
Machine learning promises to accelerate the material discovery by enabling high-throughput prediction of desirable macro-properties from atomic-level descriptors or structures. However, the limited data available about precise values of these properties have been a barrier, leading to predictive models with limited precision or the ability to generalize. This is particularly true of lattice thermal conductivity (LTC): existing datasets of precise (ab initio, DFT-based) computed values are limited to a few dozen materials with little variability. Based on such datasets, we study the impact of transfer learning on both the precision and generalizability of a deep learning model (ParAIsite). We start from an existing model (MEGNet~\cite{Chen2019}) and show that improvements are obtained by fine-tuning a pre-trained version on different tasks. Interestingly, we also show that a much greater improvement is obtained when first fine-tuning it on a large datasets of low-quality approximations of LTC (based on the AGL model) and then applying a second phase of fine-tuning with our high-quality, smaller-scale datasets. The promising results obtained pave the way not only towards a greater ability to explore large databases in search of low thermal conductivity materials but also to methods enabling increasingly precise predictions in areas where quality data are rare.
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。