arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.02235cond-mat.mtrl-scics.LG
收藏

基于不确定性量化的材料性能预测:基准研究

Materials Property Prediction with Uncertainty Quantification: A Benchmark Study

Khoury College of Computer Science, Northeastern University(东北大学 Khoury 计算机学院);Department of Computer Science and Engineering, University of South Carolina(南卡罗来纳大学计算机科学与工程系)

Daniel Varivoda, Rongzhi Dong, Sadman Sadeed Omee, Jianjun Hu

摘要:

不确定性量化(UQ)在建立稳健的、高性能的、可推广的材料性能预测模型中具有越来越重要的意义。它也可以用于主动学习,通过专注于从不确定区域获得新的训练数据来训练更好的模型。有几类UQ方法,每一类都考虑不同类型的不确定性来源。在这里,我们对基于图神经网络的材料性能预测的UQ方法进行全面评估,并评估它们如何真实地反映我们在误差界估计或主动学习中想要的不确定性。我们在四个晶体材料数据集(包括形成能、吸附能、总能量和带隙性质)上的实验结果表明,目前流行的不确定性估计的系综方法不是材料性质预测中UQ的最佳选择。为了方便社区,所有的源代码和数据集都可以在\url{https://github.com/usccolumbia/materialsUQ}上免费访问。

英文摘要:

Uncertainty quantification (UQ) has increasing importance in building robust high-performance and generalizable materials property prediction models. It can also be used in active learning to train better models by focusing on getting new training data from uncertain regions. There are several categories of UQ methods each considering different types of uncertainty sources. Here we conduct a comprehensive evaluation on the UQ methods for graph neural network based materials property prediction and evaluate how they truly reflect the uncertainty that we want in error bound estimation or active learning. Our experimental results over four crystal materials datasets (including formation energy, adsorption energy, total energy, and band gap properties) show that the popular ensemble methods for uncertainty estimation is NOT the best choice for UQ in materials property prediction. For the convenience of the community, all the source code and data sets can be accessed freely at \url{https://github.com/usccolumbia/materialsUQ}.

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。

↑