CAPMix: Robust Time Series Anomaly Detection Based on Abnormal Assumptions with Dual-Space Mixup

2025-09-08

AI Summary

Time-series anomaly detection (TSAD) faces two key challenges: severe label scarcity and distorted synthetic anomalies—often exhibiting patchy generation and inducing anomaly shift due to distributional misalignment, which blurs decision boundaries. To address these, we propose CAPMix, a controllable augmentation framework. Our method integrates anomaly hypothesis modeling, temporal convolutional networks, and hybrid augmentation. Its core contributions are: (1) CutAddPaste—a time-aware mechanism for precise, complex anomaly injection; (2) a label correction strategy that explicitly mitigates anomaly shift; and (3) dual-space MixUp operating jointly in the time domain and feature domain to enhance model robustness. Evaluated on five benchmarks—including AIOps and UCR—CAPMix achieves significant improvements over state-of-the-art methods. Moreover, it demonstrates strong robustness against label noise and annotation imperfections.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• 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: Agentic search

Abstract

Time series anomaly detection (TSAD) is a vital yet challenging task, particularly in scenarios where labeled anomalies are scarce and temporal dependencies are complex. Recent anomaly assumption (AA) approaches alleviate the lack of anomalies by injecting synthetic samples and training discriminative models. Despite promising results, these methods often suffer from two fundamental limitations: patchy generation, where scattered anomaly knowledge leads to overly simplistic or incoherent anomaly injection, and Anomaly Shift, where synthetic anomalies either resemble normal data too closely or diverge unrealistically from real anomalies, thereby distorting classification boundaries. In this paper, we propose CAPMix, a controllable anomaly augmentation framework that addresses both issues. First, we design a CutAddPaste mechanism to inject diverse and complex anomalies in a targeted manner, avoiding patchy generation. Second, we introduce a label revision strategy to adaptively refine anomaly labels, reducing the risk of anomaly shift. Finally, we employ dual-space mixup within a temporal convolutional network to enforce smoother and more robust decision boundaries. Extensive experiments on five benchmark datasets, including AIOps, UCR, SWaT, WADI, and ESA, demonstrate that CAPMix achieves significant improvements over state-of-the-art baselines, with enhanced robustness against contaminated training data. The code is available at https://github.com/alsike22/CAPMix.

Problem

• Addresses patchy anomaly generation in time series
• Mitigates anomaly shift with adaptive label refinement
• Enhances robustness against contaminated training data

Innovation

• CutAddPaste mechanism for targeted anomaly injection
• Adaptive label revision to reduce anomaly shift
• Dual-space mixup in temporal convolutional network