PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection
It addresses the problem of efficient and accurate anomaly detection in time series for applications with limited labels, offering a lightweight solution that outperforms many existing methods.
The paper tackles time series anomaly detection by proposing PatchAD, a lightweight patch-based MLP-Mixer architecture that uses contrastive learning, achieving state-of-the-art results with only 0.403M parameters and improving F1 score by 6.84%, Aff-F1 by 4.27%, and V-ROC by 2.49% across 8 datasets.
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 $0.403M$ parameters. Its efficacy is demonstrated by state-of-the-art results across $8$ datasets sourced from different application scenarios, outperforming over $30$ comparative algorithms. PatchAD significantly improves the classical F1 score by 6.84%, the Aff-F1 score by 4.27%, and the V-ROC by 2.49%. 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. The code is publicly available at https://github.com/EmorZz1G/PatchAD.