Structure-based out-of-distribution(OOD)materials property prediction:a benchmark study  

作　　者：Sadman Sadeed Omee Nihang Fu Rongzhi Dong Ming Hu Jianjun Hu 

机构地区：[1]Department of Computer Science and Engineering,University of South Carolina,Columbia,SC,USA [2]Department of Mechanical Engineering,University of South Carolina,Columbia,SC,USA

出　　处：《npj Computational Materials》2024年第1期1753-1766,共14页计算材料学(英文)

基　　金：supported in part by National Science Foundation under the grants 2110033,OAC-2311203,and 2320292.

摘　　要：In real-world materials research,machine learning(ML)models are usually expected to predict and discover novel exceptional materials that deviate from the known materials.It is thus a pressing question to provide an objective evaluation ofMLmodel performances in property prediction of out-ofdistribution(OOD)materials that are different fromthe training set.Traditional performance evaluation of materials property prediction models through the random splitting of the dataset frequently results in artificially high-performance assessments due to the inherent redundancy of typical material datasets.

关 键 词：PROPERTY PREDICTION DISTRIBUTION 

分 类 号：TG1[金属学及工艺—金属学]