Uncertainty Quantification Using Neural Networks for Molecular Property Prediction

TL;DR

This paper evaluates various uncertainty quantification methods for neural network-based molecular property prediction, revealing no single method is best across all datasets and highlighting the need for further research.

Contribution

It provides a systematic comparison of UQ methods for neural models in molecular property prediction across multiple datasets, offering practical recommendations.

Findings

No method is universally superior across datasets

Existing UQ methods have limitations in reliability

Further research is needed to improve UQ techniques

Abstract

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 benchmark datasets using multiple complementary performance metrics. Our experiments show that none of the methods we tested is unequivocally superior to all others, and none produces 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 demonstrate the benefits of further research, we conclude with a practical recommendation as to which existing techniques seem to perform well relative to others.