MAAT通过改进关联差异建模，提升时序异常检测的准确性和鲁棒性。
Mamba Adaptive Anomaly Transformer with association discrepancy for time series
- 引入稀疏注意力与Mamba状态空间模型，高效捕捉长程依赖。
- 在多个数据集上优于现有方法，异常区分度和泛化能力显著提升。
- 适合工业监控、环境感知等真实场景下的无监督异常检测任务。
时序异常检测对工业监测和环境感知至关重要，但区分异常与复杂模式仍具挑战。现有方法如Anomaly Transformer和DCdetector存在对短期上下文敏感、在噪声大、非平稳环境下效率低等问题。为此，我们提出MAAT，通过增强关联差异建模与重构质量来克服上述问题。MAAT采用稀疏注意力机制，仅聚焦相关时间步，有效降低计算冗余，实现长程依赖的高效捕捉。同时，在重构模块中引入Mamba-选择性状态空间模型，结合跳跃连接与门控注意力，提升异常定位与检测性能。大量实验表明，MAAT显著优于先前方法，在多种时序应用中展现出更优的异常可区分性与泛化能力，为真实场景下的无监督时序异常检测树立了新标准。
原文摘要 · Abstract (English)
Anomaly detection in time series is essential for industrial monitoring and environmental sensing, yet distinguishing anomalies from complex patterns remains challenging. Existing methods like the Anomaly Transformer and DCdetector have progressed, but they face limitations such as sensitivity to short-term contexts and inefficiency in noisy, non-stationary environments. To overcome these issues, we introduce MAAT, an improved architecture that enhances association discrepancy modeling and reconstruction quality. MAAT features Sparse Attention, efficiently capturing long-range dependencies by focusing on relevant time steps, thereby reducing computational redundancy. Additionally, a Mamba-Selective State Space Model is incorporated into the reconstruction module, utilizing a skip connection and Gated Attention to improve anomaly localization and detection performance. Extensive experiments show that MAAT significantly outperforms previous methods, achieving better anomaly distinguishability and generalization across various time series applications, setting a new standard for unsupervised time series anomaly detection in real-world scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。