Bayesian Graph Neural Networks for Molecular Property Prediction
Biomolecules
2020-12-04 v1 Machine Learning
Abstract
Graph neural networks for molecular property prediction are frequently underspecified by data and fail to generalise to new scaffolds at test time. A potential solution is Bayesian learning, which can capture our uncertainty in the model parameters. This study benchmarks a set of Bayesian methods applied to a directed MPNN, using the QM9 regression dataset. We find that capturing uncertainty in both readout and message passing parameters yields enhanced predictive accuracy, calibration, and performance on a downstream molecular search task.
Keywords
Cite
@article{arxiv.2012.02089,
title = {Bayesian Graph Neural Networks for Molecular Property Prediction},
author = {George Lamb and Brooks Paige},
journal= {arXiv preprint arXiv:2012.02089},
year = {2020}
}
Comments
Presented at NeurIPS 2020 Machine Learning for Molecules workshop