A benchmark study on reliable molecular supervised learning via Bayesian learning

2020/06/12 by Doyeong Hwang, Hwang, Doyeong, Grace Lee +7 · 4 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Bayesian inference #Bayesian network #Bayesian probability #Benchmark (surveying) #Computational Drug Discovery Methods #Computer science #Correctness #Drug discovery #FOS: Computer and information sciences #Generalization error #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Machine learning #Metabolomics and Mass Spectrometry Studies #Naive Bayes classifier #Reliability (semiconductor) #Support vector machine #Variable-order Bayesian network #Virtual screening #Wake-sleep algorithm #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2006.07021

published in arXiv (Cornell University) (Cornell University) · To be appeared in ICML 2020 Workshop "Uncertainty and Robustness in Deep Learning"

openalex publication_date 2020/06/12 · openalex created_date 2020/06/19 · arxiv created 2020/07/01 · arxiv updated 2020/07/02 · openalex updated_date 2026/07/28

Abstract

Virtual screening aims to find desirable compounds from chemical library by using computational methods. For this purpose with machine learning, model outputs that can be interpreted as predictive probability will be beneficial, in that a high prediction score corresponds to high probability of correctness. In this work, we present a study on the prediction performance and reliability of graph neural networks trained with the recently proposed Bayesian learning algorithms. Our work shows that Bayesian learning algorithms allow well-calibrated predictions for various GNN architectures and classification tasks. Also, we show the implications of reliable predictions on virtual screening, where Bayesian learning may lead to higher success in finding hit compounds.

Citations

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Residual Gated Graph ConvNets
• Averaging Weights Leads to Wider Optima and Better Generalization
• How Powerful are Graph Neural Networks?
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Weight Uncertainty in Neural Networks
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Deep Ensembles: A Loss Landscape Perspective
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization

Cited by

• Molecular Similarity in Machine Learning of Energies in Chemical Reaction Networks

Related

• A comprehensive study on the prediction reliability of graph neural networks for virtual screening
• Bayesian Graph Neural Networks for Molecular Property Prediction
• Large-scale Pretraining Improves Sample Efficiency of Active Learning based Molecule Virtual Screening
• Leveraging Classical Algorithms for Graph Neural Networks
• Uncertainty quantification of molecular property prediction using Bayesian neural network models