通过频段切片与通道融合，提升多变量时间序列异常检测精度
CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching
- 将频域切分为频段，捕捉细微频率特征
- 提出通道融合模块，自动识别相关通道并抑制干扰
- 在22个数据集上达到领先效果，适合工业异常监测
多变量时间序列异常检测面临异构子序列异常的挑战。基于重构的方法虽在频域学习正常模式以检测多样异常，但仍难以捕捉精细频域特征与通道相关性。为此，本文提出CATCH框架，通过频域切片生成频段，增强对细粒度频率特征的感知能力。设计通道融合模块（CFM），包含逐块掩码生成器与掩码注意力机制，驱动其通过双层多目标优化算法，迭代发现恰当的块级通道相关性，聚类相关通道并隔离无关通道的影响。在10个真实数据集与12个合成数据集上的大量实验表明，CATCH性能达到当前最优。代码与数据集已开源：https://github.com/decisionintelligence/CATCH。
原文摘要 · Abstract (English)
Anomaly detection in multivariate time series is challenging as heterogeneous subsequence anomalies may occur. Reconstruction-based methods, which focus on learning normal patterns in the frequency domain to detect diverse abnormal subsequences, achieve promising results, while still falling short on capturing fine-grained frequency characteristics and channel correlations. To contend with the limitations, we introduce CATCH, a framework based on frequency patching. We propose to patchify the frequency domain into frequency bands, which enhances its ability to capture fine-grained frequency characteristics. To perceive appropriate channel correlations, we propose a Channel Fusion Module (CFM), which features a patch-wise mask generator and a masked-attention mechanism. Driven by a bi-level multi-objective optimization algorithm, the CFM is encouraged to iteratively discover appropriate patch-wise channel correlations, and to cluster relevant channels while isolating adverse effects from irrelevant channels. Extensive experiments on 10 real-world datasets and 12 synthetic datasets demonstrate that CATCH achieves state-of-the-art performance. We make our code and datasets available at https://github.com/decisionintelligence/CATCH.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。