Uncertainty Quantification for Molecular Property Predictions with Graph Neural Architecture Search

Abstract

Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.

References in corpus (8)

• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• A Survey of Uncertainty in Deep Neural Networks
• ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
• Uncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantification
• Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imaging
• AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification

Cited by in corpus (1)

• Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design