CLEANet: Robust and Efficient Anomaly Detection in Contaminated Multivariate Time Series

2025-10-26

AI Summary

To address model distortion, overfitting, and high inference latency caused by training data contamination—i.e., label noise and latent anomalies—in industrial multivariate time series (MTS) anomaly detection, this paper proposes a robust and efficient detection framework. Methodologically, it introduces: (1) a contamination-resilient training mechanism integrating adaptive reconstruction weighting with clustering-guided contrastive learning to mitigate label noise; and (2) a lightweight conjugate MLP architecture that explicitly decouples temporal dynamics from cross-feature dependencies, significantly reducing computational complexity. Evaluated on five public benchmarks against ten state-of-the-art methods, the framework achieves an average 73.04% improvement in F1-score and reduces inference time by 81.28%. Moreover, it demonstrates strong transferability, enabling plug-and-play performance enhancement for other anomaly detection models.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Multivariate time series (MTS) anomaly detection is essential for maintaining the reliability of industrial systems, yet real-world deployment is hindered by two critical challenges: training data contamination (noises and hidden anomalies) and inefficient model inference. Existing unsupervised methods assume clean training data, but contamination distorts learned patterns and degrades detection accuracy. Meanwhile, complex deep models often overfit to contamination and suffer from high latency, limiting practical use. To address these challenges, we propose CLEANet, a robust and efficient anomaly detection framework in contaminated multivariate time series. CLEANet introduces a Contamination-Resilient Training Framework (CRTF) that mitigates the impact of corrupted samples through an adaptive reconstruction weighting strategy combined with clustering-guided contrastive learning, thereby enhancing robustness. To further avoid overfitting on contaminated data and improve computational efficiency, we design a lightweight conjugate MLP that disentangles temporal and cross-feature dependencies. Across five public datasets, CLEANet achieves up to 73.04% higher F1 and 81.28% lower runtime compared with ten state-of-the-art baselines. Furthermore, integrating CRTF into three advanced models yields an average 5.35% F1 gain, confirming its strong generalizability.

Problem

• Detecting anomalies in contaminated multivariate time series data
• Addressing training data contamination and inefficient model inference
• Improving robustness and computational efficiency in anomaly detection

Innovation

• Adaptive reconstruction weighting strategy mitigates contamination
• Clustering-guided contrastive learning enhances detection robustness
• Lightweight conjugate MLP disentangles temporal dependencies efficiently