Uncertainty quantification using neural networks for molecular property prediction

作     者：Hirschfeld, Lior Swanson, Kyle Yang, Kevin Barzilay, Regina Coley, Connor W. 

作者机构：Computer Science and Artificial Intelligence Laboratory MIT CambridgeMA02139 United States Department of Pure Mathematics and Mathematical Statistics University of Cambridge CambridgeCB3 0WB United Kingdom Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States Department of Chemical Engineering MIT CambridgeMA02139 United States 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2020年

核心收录：

主　　题：Uncertainty analysis 

摘      要：Uncertainty quantification (UQ) is an important component of molecular property prediction, particularly for drug discovery applications where model predictions direct experimental design and where unanticipated imprecision wastes valuable time and resources. The need for UQ is especially acute for neural models, which are becoming increasingly standard yet are challenging to interpret. While several approaches to UQ have been proposed in the literature, there is no clear consensus on the comparative performance of these models. In this paper, we study this question in the context of regression tasks. We systematically evaluate several methods on five regression datasets using multiple complementary performance metrics. Our experiments show that none of the methods we tested is unequivocally superior to all others, and none produce a particularly reliable ranking of errors across multiple datasets. While we believe these results show that existing UQ methods are not sufficient for all common use cases and further research is needed, we conclude with a practical recommendation as to which existing techniques seem to perform well relative to others. Copyright © 2020, The Authors. All rights reserved.