一句话：提出CAPMix，一种基于先验引导注入的可控异常增强框架，通过标签修正与双空间mixup提升噪声和动态环境下KPI异常检测的鲁棒性。
AIOps中KPI异常检测对大规模服务可靠性至关重要。生产环境中的KPI流具有高维、非平稳、受噪声和部署变更影响等特点，真实故障与良性波动难以区分。现有方法多假设正常历史或依赖注入异常训练，但注入模式与真实故障模式不匹配，导致决策边界偏移（Anomaly Shift）。CAPMix是一个可控异常增强框架，通过先验引导注入生成真实时间行为，并结合标签修正与双空间mixup，提升在污染和混合数据下的鲁棒性。在公开AIOps和时间序列基准上，CAPMix持续优于现有最优方法；已部署于大规模生产系统，降低误报并提高监控可靠性。同时发布真实数据集以促进鲁棒KPI异常检测研究。
Time-series anomaly detection is crucial in AIOps for maintaining large-scale service reliability. In production, streams of Key Performance Indicators (KPI) are high-dimensional, non-stationary, and affected by noise, deployment changes, and latent anomalies, making real failures hard to distinguish from benign variation. Most existing methods assume either normality (learning from “normal” history) or rely on injected anomalies for training. Yet injected patterns often misalign with real failure modes, skewing decision boundaries – aka. Anomaly Shift. We propose CAPMix, a controllable anomaly augmentation framework with prior-guided injection for realistic temporal behaviors. CAPMix combines label revision and dual-space mixup to enhance robustness under contaminated and mixed data. CAPMix consistently outperforms state-of-the-art methods on public AIOps and time-series benchmarks. It has been deployed in a large-scale production system, reducing false alarms and improving monitoring reliability. A real-world dataset is also released to enrich the research on robust KPI anomaly detection.
@inproceedings{paperbot12596,
title = {CAPMix: Robust KPI Anomaly Detection for AIOps in Noisy and Dynamic Environments},
author = {Xudong Mou and Rui Wang and Tiejun Wang and Zexin Wu and Fangda Guo and Jie Sun and Shiru Chen and Penghao Zhang and Tiezi Zhang and Tianyu Wo and Hao Peng and Chunming Hu and Xudong Liu and Renyu Yang},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834487}
}