面向真实世界预测的扩展计算材料数据库中Sim2Real迁移学习的标度律
Scaling Law of Sim2Real Transfer Learning in Expanding Computational Materials Databases for Real-World Predictions
AI总结：
本文通过聚合物和无机材料的三项预测任务，揭示了Sim2Real迁移学习中真实系统预测误差随计算数据规模呈幂律下降的标度律，为计算材料数据库的样本量确定、物理与计算实验等效性评估及数据生产协议设计提供指导。
摘要：
为解决实验材料数据有限的问题，人们正基于高通量计算实验（如分子动力学模拟）开发大规模物理性质数据库。已有研究表明，将在计算数据库上预训练的预测器微调至真实系统，相比从头学习可获得更优异的泛化能力。本研究展示了材料科学中若干机器学习任务在仿真到真实（Sim2Real）迁移学习中的标度律。针对聚合物和无机材料的三项预测任务案例研究表明，随着计算数据规模的增大，真实系统上的预测误差按幂律下降。观察该标度行为可为数据库开发提供多方面启示，例如确定达到期望性能所需的样本量、识别物理实验与计算实验的等效样本量，以及指导下游真实世界任务的数据生产协议设计。
英文摘要：
To address the challenge of limited experimental materials data, extensive physical property databases are being developed based on high-throughput computational experiments, such as molecular dynamics simulations. Previous studies have shown that fine-tuning a predictor pretrained on a computational database to a real system can result in models with outstanding generalization capabilities compared to learning from scratch. This study demonstrates the scaling law of simulation-to-real (Sim2Real) transfer learning for several machine learning tasks in materials science. Case studies of three prediction tasks for polymers and inorganic materials reveal that the prediction error on real systems decreases according to a power-law as the size of the computational data increases. Observing the scaling behavior offers various insights for database development, such as determining the sample size necessary to achieve a desired performance, identifying equivalent sample sizes for physical and computational experiments, and guiding the design of data production protocols for downstream real-world tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
