Lamb, G;
Paige, B;
(2020)
Bayesian Graph Neural Networks for Molecular Property Prediction.
In:
Proceedings of the 2020 NeurIPS Workshop on Machine Learning for Molecules.
Neural Information Processing Systems
Preview |
Text
2012.02089v1.pdf - Accepted Version Download (483kB) | Preview |
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Bayesian Graph Neural Networks for Molecular Property Prediction |
| Event: | 2020 NeurIPS Workshop on Machine Learning for Molecules |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://ml4molecules.github.io/ |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | q-bio.BM, q-bio.BM, cs.LG |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10124712 |
Archive Staff Only
 |
View Item |
