SCAN: Enhance Time Series Anomaly Detection via Multi-Scale Neighborhood-Centered Clustering

2026-06-17

AI Summary

This work addresses the imbalance between over-generalization and under-generalization inherent in reconstruction-based time series anomaly detection methods. To mitigate this issue, the authors propose an enhanced reconstruction framework grounded in multi-scale neighborhood center clustering. The approach introduces cluster centers of normal patterns as reconstruction constraints at the representation level and integrates reconstruction error with cluster membership probability to form a dual anomaly scoring mechanism at the decision level. Furthermore, multi-view clustering is employed to refine neighborhood center representations, thereby improving overall clustering quality. Experimental results demonstrate that the proposed method significantly outperforms state-of-the-art techniques across multiple real-world datasets spanning diverse domains, effectively alleviating the generalization imbalance commonly observed in reconstruction-based models.

Abstract

Time series anomaly detection plays a crucial role in a wide range of real-world applications. Reconstruction-based methods have become the mainstream paradigm, but they suffer from over-generalization and under-generalization problems, which are challenging to balance. To address this, we introduce multi-scale clustering to enhance reconstruction-based methods. At the representation level, we integrate the cluster center representations of normal patterns to constrain the model to target representative normal patterns for reconstruction, preventing dominance of powerful capacity and representation capability. At the anomaly criterion level, we derive anomaly confidence score based on cluster membership probability and combine it with reconstruction error, providing dual criteria for detection. Furthermore, the effectiveness of the cluster center representations and anomaly confidence score depends on the clustering performance. Accordingly, we extract neighborhood-centered representations for multi-view clustering to improve clustering performance. Extensive experiments on multiple real-world datasets from diverse application domains demonstrate the state-of-the-art performance of SCAN.

Problem

• time series anomaly detection
• reconstruction-based methods
• over-generalization
• under-generalization
• clustering

Innovation

• multi-scale clustering
• neighborhood-centered representation
• reconstruction-based anomaly detection
• anomaly confidence score
• time series