Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning
2026-07-01 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors address the difficulty of spotting small and noisy unusual patterns in complex industrial time series data without labeled examples. They propose a new approach that uses active learning to improve unsupervised models by teaching them to better understand time sequences and handle normal and abnormal cases differently. Their method was tested on multiple datasets and models, showing about a 12% improvement in detection accuracy. This approach can be added to existing systems to make them better at finding subtle anomalies.
time series dataanomaly detectionunsupervised learningactive learningmasked reconstructionminimax learningtemporal dependenciesAUC (Area Under Curve)noise robustnessmultivariate data
Authors
Seung Hun Han, Hyeongwon Kang, Jinwoo Park, Pilsung Kang
Abstract
Despite the increasing sophistication of industrial AI systems, the ability to reliably detect subtle and noisy anomalies in complex time series data remains a critical yet unresolved challenge. In large-scale industrial applications, labeling time series data is often prohibitively expensive and time-consuming, making unsupervised learning a practical and widely adopted approach. However, existing unsupervised methods frequently struggle to distinguish near-normal anomalies from normal patterns and are vulnerable to noise contamination within normal samples. To address these limitations, we propose a novel framework that leverages active learning to iteratively enhance the performance of unsupervised models. Our framework's core contributions are (1) a masked time-series reconstruction feedback strategy that forces the model to learn robust temporal dependencies, and (2) a minimax learning strategy that promotes robustness by differentially treating normal and abnormal samples. This process encourages the model to better capture the dynamics of subtle and noisy patterns. The proposed framework is evaluated across 28 test cases involving four multivariate time-series datasets and seven unsupervised backbone models. Experimental results demonstrate a 12.39% improvement in AUC compared to the original models, confirming that our method can be readily integrated into existing unsupervised reconstruction-based anomaly detection systems to significantly enhance their performance.