Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection
This work addresses the need for trustworthy anomaly detection in high-stake applications like manufacturing, though it is incremental as it builds on existing Bayesian methods.
The paper tackled the lack of uncertainty quantification in autoencoders for anomaly detection by adopting Bayesian autoencoders to quantify total anomaly uncertainty, and demonstrated their effectiveness on benchmark and real manufacturing datasets.
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.