Calibrated Uncertainty for Molecular Property Prediction using Ensembles of Message Passing Neural Networks
This work addresses the need for reliable uncertainty quantification in computational chemistry, which is crucial for decision-making in molecular analysis, though it is incremental as it builds on existing message passing neural networks.
The authors tackled the problem of unreliable uncertainty estimates in machine learning models for molecular property prediction by developing a unified framework that accounts for both aleatoric and epistemic uncertainty and recalibrates predictions on unseen data. They demonstrated accurate predictions with well-calibrated uncertainty on the QM9 and PC9 benchmark datasets.
Data-driven methods based on machine learning have the potential to accelerate computational analysis of atomic structures. In this context, reliable uncertainty estimates are important for assessing confidence in predictions and enabling decision making. However, machine learning models can produce badly calibrated uncertainty estimates and it is therefore crucial to detect and handle uncertainty carefully. In this work we extend a message passing neural network designed specifically for predicting properties of molecules and materials with a calibrated probabilistic predictive distribution. The method presented in this paper differs from previous work by considering both aleatoric and epistemic uncertainty in a unified framework, and by recalibrating the predictive distribution on unseen data. Through computer experiments, we show that our approach results in accurate models for predicting molecular formation energies with well calibrated uncertainty in and out of the training data distribution on two public molecular benchmark datasets, QM9 and PC9. The proposed method provides a general framework for training and evaluating neural network ensemble models that are able to produce accurate predictions of properties of molecules with well calibrated uncertainty estimates.