PatchAD: A Lightweight Patch-Based MLP-Mixer for Time Series Anomaly Detection
Zhijie Zhong, Zhiwen Yu, Yiyuan Yang, Weizheng Wang, Kaixiang Yang, C. L. Philip Chen
Abstract
Time series anomaly detection is a pivotal task in data analysis, 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 limit 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 <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.403 M</b> parameters. Its efficacy is demonstrated by state-of-the-art results across <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">8</b> datasets sourced from different application scenarios, outperforming over <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">30</b> comparative algorithms. PatchAD significantly improves the classical F1 score by <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6.84%</b>, the Aff-F1 score by <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4.27%</b>, and the V-ROC by <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.49%</b>. Simultaneously, an in-depth analysis of the mechanisms underlying PatchAD has been conducted from both theoretical and experimental perspectives, validating the design motivations of the model.