PatchAD：一种用于时间序列异常检测的轻量级基于补丁的MLP-Mixer
PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection
AI总结：
针对时间序列异常检测中标签缺失、现有重构类方法表征能力有限且深度学习方法不够轻量的问题，提出基于多尺度补丁的轻量MLP-Mixer架构PatchAD，结合对比学习与双投影约束模块，在8个数据集上超越30余种算法，性能提升显著。
摘要：
时间序列异常检测是数据分析中的一项关键任务，但其面临在标签缺失场景下区分正常与异常模式的挑战。以往研究大多采用基于重构的方法，这限制了模型的表征能力。此外，现有的基于深度学习的方法不够轻量。针对这些问题，我们提出了PatchAD，这是一种新型、高效的基于多尺度补丁的MLP-Mixer架构，利用对比学习进行表征提取和异常检测。凭借其四个不同的MLP Mixer和创新的双投影约束模块，PatchAD缓解了潜在的模型退化问题，并提供了一种轻量级解决方案，仅需0.403M个参数。其有效性通过来自不同应用场景的8个数据集上的最优结果得到了证明，性能超过了30多种对比算法。PatchAD将经典F1分数显著提升了6.84%，Aff-F1分数提升了4.27%，V-ROC提升了2.49%。同时，我们从理论和实验两个角度对PatchAD的潜在机制进行了深入分析，验证了模型的设计动机。代码公开于https://github.com/EmorZz1G/PatchAD。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
