Contextual and Seasonal LSTMs for Time Series Anomaly Detection
Lingpei Zhang, Qingming Li, Yong Yang, Jiahao Chen, Rui Zeng, Chenyang Lyu, Shouling Ji
Abstract
Univariate time series (UTS), where each timestamp records a single variable, serve as crucial indicators in web systems and cloud servers. Anomaly detection in UTS plays an essential role in both data mining and system reliability management. However, existing reconstruction-based and prediction-based methods struggle to capture certain subtle anomalies, particularly small point anomalies and slowly rising anomalies. To address these challenges, we propose a novel prediction-based framework named Contextual and Seasonal LSTMs (CS-LSTMs). CS-LSTMs are built upon a noise decomposition strategy and jointly leverage contextual dependencies and seasonal patterns, thereby strengthening the detection of subtle anomalies. By integrating both time-domain and frequency-domain representations, CS-LSTMs achieve more accurate modeling of periodic trends and anomaly localization. Extensive evaluations on public benchmark datasets demonstrate that CS-LSTMs consistently outperform state-of-the-art methods, highlighting their effectiveness and practical value in robust time series anomaly detection.
BibTeX
@inproceedings{
zhang2026contextual,
title={Contextual and Seasonal {LSTM}s for Time Series Anomaly Detection},
author={Lingpei Zhang and Qingming Li and Yong Yang and Jiahao Chen and Rui Zeng and Chenyang Lyu and Shouling Ji},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=2VtveTkmzW}
}