CLEANet: Robust and Efficient Anomaly Detection in Contaminated Multivariate Time Series
Preprint
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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Reconstruction-based anomaly detection for multivariate time series using contrastive generative adversarial networksInformation Processing & Management, 2023
- ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly DetectionProceedings of the VLDB Endowment, 2023
- Multiview Graph Contrastive Learning for Multivariate Time-Series Anomaly Detection in IoTIEEE Internet of Things Journal, 2023
- Contrastive autoencoder for anomaly detection in multivariate time seriesInformation Sciences, 2022
- Twin Contrastive Learning for Online ClusteringInternational Journal of Computer Vision, 2022
- A Review on Outlier/Anomaly Detection in Time Series DataACM Computing Surveys, 2021
- A Spatiotemporal Deep Learning Approach for Unsupervised Anomaly Detection in Cloud SystemsIEEE Transactions on Neural Networks and Learning Systems, 2020
- Anomaly Detection for IoT Time-Series Data: A SurveyIEEE Internet of Things Journal, 2019
- A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational AutoencoderIEEE Robotics and Automation Letters, 2018
- Microservices Architecture Enables DevOps: Migration to a Cloud-Native ArchitectureIEEE Software, 2016