Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection

2026-05-25

AI Summary

This work addresses the challenge of detecting subtle, long-duration anomalies in time series, a task where existing deep learning methods struggle due to limited generalization in classification paradigms and mask misalignment in reconstruction-based approaches. The authors propose CoAD, a novel framework that uniquely integrates Outlier Exposure with Masked Autoencoders through a probability-guided soft masking mechanism. This enables synergistic optimization between classification and reconstruction modules: the classifier generates soft masks to guide reconstruction, while the reconstruction output enhances the classifier’s generalization, forming a complementary closed loop. By refining classification granularity and better leveraging frequency-domain information within a lightweight architecture, CoAD achieves superior detection accuracy and faster inference than state-of-the-art methods across multiple benchmarks, making it well-suited for large-scale real-time applications.

Abstract

Time series anomaly detection (TSAD) has long been a hot research topic in data mining due to its various applications. Recent studies challenge the effectiveness of popular deep learning methods for TSAD, suggesting their failure in detecting subtle and prolonged anomalies. Outlier Exposure (OE) and Masked Autoencoder (MAE) emerge as two promising paradigms (classification and reconstruction) for solving the above problems. However, OE-based methods are constrained by poor generalization, while MAE-based methods are limited by masking misalignment issues. To address these limitations, this paper proposes a novel framework, CoAD, which unifies the two paradigms to leverage their complementary strengths while mitigating their respective weaknesses. In this framework, the classification module generates probability-informed soft masks for the reconstruction module, which in turn alleviates the generalization problem of the classification module. This cooperative design enables CoAD to effectively detect subtle and complex anomalies that are often overlooked by existing methods. Additionally, the classification module is carefully designed to resolve issues related to improper classification granularity and the neglect of frequency information. Extensive experiments on high-quality benchmark datasets, conducted under rigorous evaluation protocols, demonstrate that CoAD significantly outperforms both state-of-the-art deep learning and traditional data mining methods, highlighting the potential of deep learning in TSAD. Moreover, CoAD is lightweight and substantially faster than existing SOTA methods, demonstrating its practical value for large-scale, real-time applications.

Problem

• time series anomaly detection
• subtle anomalies
• prolonged anomalies
• Outlier Exposure
• Masked Autoencoder

Innovation

• Cooperative Anomaly Detection
• Outlier Exposure
• Masked Autoencoder
• Time Series Anomaly Detection
• Soft Masking