CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling

2025-10-14

AI Summary

Existing time-series anomaly detection methods typically rely on fixed sliding windows and single-scale modeling, failing to capture the dynamic cross-scale correlations and long-range contextual dependencies inherent in anomalous patterns. To address this, we propose CrossAD—a novel framework featuring a cross-scale reconstruction mechanism and a learnable query bank, explicitly modeling dynamic interactions among multi-scale features. By incorporating global context aggregation, CrossAD transcends local window constraints, enabling joint optimization of fine-grained and coarse-grained representations. Extensive experiments across multiple real-world datasets, evaluated under nine standard metrics, demonstrate that CrossAD consistently outperforms state-of-the-art methods, achieving an average 3.2% improvement in F1-score. Moreover, it exhibits enhanced robustness and generalization capability across diverse anomaly types and data distributions.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Time-Series/Data Streams
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Time series anomaly detection plays a crucial role in a wide range of real-world applications. Given that time series data can exhibit different patterns at different sampling granularities, multi-scale modeling has proven beneficial for uncovering latent anomaly patterns that may not be apparent at a single scale. However, existing methods often model multi-scale information independently or rely on simple feature fusion strategies, neglecting the dynamic changes in cross-scale associations that occur during anomalies. Moreover, most approaches perform multi-scale modeling based on fixed sliding windows, which limits their ability to capture comprehensive contextual information. In this work, we propose CrossAD, a novel framework for time series Anomaly Detection that takes Cross-scale associations and Cross-window modeling into account. We propose a cross-scale reconstruction that reconstructs fine-grained series from coarser series, explicitly capturing cross-scale associations. Furthermore, we design a query library and incorporate global multi-scale context to overcome the limitations imposed by fixed window sizes. Extensive experiments conducted on multiple real-world datasets using nine evaluation metrics validate the effectiveness of CrossAD, demonstrating state-of-the-art performance in anomaly detection.

Problem

• Captures dynamic cross-scale associations in time series
• Overcomes limitations of fixed sliding window approaches
• Enhances anomaly detection through cross-window modeling

Innovation

• Cross-scale reconstruction captures fine-grained series associations
• Query library overcomes fixed window size limitations
• Global multi-scale context enhances anomaly detection performance