# Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning

arXiv: https://arxiv.org/abs/1902.00925 · HTML: https://mlsanity.com/paper/1902.00925/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2019.

## Built on by (most cited first, 21 of 21)

- [Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification](https://mlsanity.com/paper/2110.14012/) (2021)
- [On Statistical Bias In Active Learning: How and When To Fix It](https://mlsanity.com/paper/2101.11665/) (2021)
- [A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?](https://mlsanity.com/paper/2402.05015/) (2024)
- [GAUCHE: A Library for Gaussian Processes in Chemistry](https://mlsanity.com/paper/2212.04450/) (2022)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [Assigning Confidence to Molecular Property Prediction](https://mlsanity.com/paper/2102.11439/) (2021)
- [MUBen: Benchmarking the Uncertainty of Molecular Representation Models](https://mlsanity.com/paper/2306.10060/) (2023)
- [Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS](https://mlsanity.com/paper/2212.01574/) (2022)
- [Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions](https://mlsanity.com/paper/2307.15073/) (2023)
- [Lo-Hi: Practical ML Drug Discovery Benchmark](https://mlsanity.com/paper/2310.06399/) (2023)
- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [Distributed Representations of Atoms and Materials for Machine Learning](https://mlsanity.com/paper/2107.14664/) (2021)
- [Uncertainty-Aware Robust Learning on Noisy Graphs](https://mlsanity.com/paper/2306.08210/) (2023)
- [Ranking over Regression for Bayesian Optimization and Molecule Selection](https://mlsanity.com/paper/2410.09290/) (2024)
- [Quantifying sources of uncertainty in drug discovery predictions with probabilistic models](https://mlsanity.com/paper/2105.09474/) (2021)
- [Stein Variational Evolution Strategies](https://mlsanity.com/paper/2410.10390/) (2024)
- [Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction](https://mlsanity.com/paper/2205.11279/) (2022)
- [Efficient Chemical Space Exploration Using Active Learning Based on Marginalized Graph Kernel: an Application for Predicting the Thermodynamic Properties of Alkanes with Molecular Simulation](https://mlsanity.com/paper/2209.00514/) (2022)
- [Current Methods for Drug Property Prediction in the Real World](https://mlsanity.com/paper/2309.17161/) (2023)
- [Active Learning of Molecular Data for Task-Specific Objectives](https://mlsanity.com/paper/2408.11191/) (2024)
- [GNN's Uncertainty Quantification using Self-Distillation](https://mlsanity.com/paper/2506.20046/) (2025)

## Abstract (arXiv)

Predicting bioactivity and physical properties of small molecules is a central challenge in drug discovery. Deep learning is becoming the method of choice but studies to date focus on mean accuracy as the main metric. However, to replace costly and mission-critical experiments by models, a high mean accuracy is not enough: Outliers can derail a discovery campaign, thus models need reliably predict when it will fail, even when the training data is biased; experiments are expensive, thus models need to be data-efficient and suggest informative training sets using active learning. We show that uncertainty quantification and active learning can be achieved by Bayesian semi-supervised graph convolutional neural networks. The Bayesian approach estimates uncertainty in a statistically principled way through sampling from the posterior distribution. Semi-supervised learning disentangles representation learning and regression, keeping uncertainty estimates accurate in the low data limit and allowing the model to start active learning from a small initial pool of training data. Our study highlights the promise of Bayesian deep learning for chemistry.