15
5

PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection

Abstract

Anomaly detection in time series analysis is a pivotal task, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios. While prior studies have largely employed reconstruction-based approaches, which limits the models' representational capacities. Moreover, existing deep learning-based methods are not sufficiently lightweight. Addressing these issues, we present PatchAD, our novel, highly efficient multiscale patch-based MLP-Mixer architecture that utilizes contrastive learning for representation extraction and anomaly detection. With its four distinct MLP Mixers and innovative dual project constraint module, PatchAD mitigates potential model degradation and offers a lightweight solution, requiring only 3.23.2MB. Its efficacy is demonstrated by state-of-the-art results across 99 datasets sourced from different application scenarios, outperforming over 3030 comparative algorithms. PatchAD significantly improves the classical F1 score by 50.5%50.5\%, the Aff-F1 score by 7.8%7.8\%, and the AUC by 10.0%10.0\%. The code is publicly available. \url{https://github.com/EmorZz1G/PatchAD}

View on arXiv
Comments on this paper