摘要
In order to make accurate predictions of material properties,current machine-learning approaches generally require large amounts of data,which are often not available in practice.In this work,MODNet,an all-round framework,is presented which relies on a feedforward neural network,the selection of physically meaningful features,and when applicable,joint-learning.Next to being faster in terms of training time,this approach is shown to outperform current graph-network models on small datasets.In particular,the vibrational entropy at 305 K of crystals is predicted with a mean absolute test error of 0.009 meV/K/atom(four times lower than previous studies).Furthermore,joint learning reduces the test error compared to single-target learning and enables the prediction of multiple properties at once,such as temperature functions.Finally,the selection algorithm highlights the most important features and thus helps to understand the underlying physics.
基金
The authors acknowledge useful discussions and help from M.L.Evans about the MODNet development and from R.Ouyang and L.Ghiringhelli about the SISSO framework.P.-P.D.B.and G.-M.R.are grateful to the FRS-FNRS for financial support.Computational resources have been provided by the supercomputing facilities of the Universitécatholique de Louvain(CISM/UCL)and the Consortium desÉquipements de Calcul Intensif en Fédération Wallonie Bruxelles(CÉCI)funded by the Fond de la Recherche Scientifique de Belgique(FRS-FNRS)under convention 2.5020.11 and by the Walloon Region.G.H.acknowledges funding by the U.S.Department of Energy,Office of Science,Office of Basic Energy Sciences,Materials Sciences and Engineering Division,under Contract DE-AC02-05-CH11231:Materials Project program KC23MP.