Uncertainty estimation in deep learning-based property models: Graph neural networks applied to the critical properties

Deep learning and graph-based models have gained popularity in various life science applications such as property modeling, achieving state-of-the-art performance. However, the quantification of prediction uncertainty in these models is less studied and is not applied in the low dataset size regime, which characterizes many chemical engineering-related molecular properties. In this work, we apply two graph-based models to model the critical- temperature, pressure, and volume and apply three techniques (the bootstrap, the ensemble, and the dropout) to quantify the prediction uncertainty. The overall model confidence is evaluated using the coverage. The results suggest that graph-based models perform better compared with current group-contribution-based property modeling techniques while eliminating the tedious task of developing molecular descriptors.

Automated summary

Deep learning and graph-based models are widely used in life science applications for property modeling and have achieved advanced performance. However, quantifying prediction uncertainty in chemical engineering-related molecular properties is challenging. This study applies graph-based models and three techniques to address this issue.