CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching
This work addresses anomaly detection in multivariate time series, which is critical for applications like industrial monitoring, but it is incremental as it builds on existing reconstruction-based methods.
The paper tackles the challenge of detecting heterogeneous subsequence anomalies in multivariate time series by introducing CATCH, a framework that uses frequency patching and a Channel Fusion Module to capture fine-grained frequency characteristics and channel correlations, achieving state-of-the-art performance on 10 real-world and 12 synthetic datasets.
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.