论文标题
材料属性预测具有不确定性量化：基准研究
Materials Property Prediction with Uncertainty Quantification: A Benchmark Study
论文作者
论文摘要
不确定性量化（UQ）在构建强大的高性能和可推广材料的财产预测模型方面具有越来越重要的重要性。它也可以用于积极学习中，通过专注于从不确定地区获取新的培训数据来培训更好的模型。 UQ方法有几类考虑不同类型的不确定性来源的方法。在这里，我们对基于图形神经网络的材料属性预测的UQ方法进行了全面评估，并评估了它们如何真正反映我们在错误约束估计或主动学习中所需的不确定性。我们对四个晶体材料数据集的实验结果（包括形成能，吸附能，总能量和带隙性能）表明，流行的不确定性估计的集合方法不是材料属性预测中UQ的最佳选择。为了方便社区，可以通过\ url {https://github.com/usccolumbia/materialsuq}自由访问所有源代码和数据集。
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}.
