Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection

TL;DR

This paper introduces Bayesian autoencoders that quantify uncertainty in anomaly detection, enhancing trustworthiness in high-stakes applications by combining epistemic and aleatoric uncertainties and evaluating performance with new metrics.

Contribution

The work formulates Bayesian autoencoders for uncertainty quantification in anomaly detection, incorporating accuracy-rejection curves and weighted accuracy as evaluation metrics.

Findings

BAEs effectively quantify total anomaly uncertainty.

Uncertainty-aware classification improves anomaly detection performance.

Experimental results on benchmark and manufacturing datasets validate the approach.

Abstract

Despite numerous studies of deep autoencoders (AEs) for unsupervised anomaly detection, AEs still lack a way to express uncertainty in their predictions, crucial for ensuring safe and trustworthy machine learning systems in high-stake applications. Therefore, in this work, the formulation of Bayesian autoencoders (BAEs) is adopted to quantify the total anomaly uncertainty, comprising epistemic and aleatoric uncertainties. To evaluate the quality of uncertainty, we consider the task of classifying anomalies with the additional option of rejecting predictions of high uncertainty. In addition, we use the accuracy-rejection curve and propose the weighted average accuracy as a performance metric. Our experiments demonstrate the effectiveness of the BAE and total anomaly uncertainty on a set of benchmark datasets and two real datasets for manufacturing: one for condition monitoring, the other for quality inspection.