意料之外的注意力机制：可预测查询动态在时间序列异常检测中的应用

Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection

March 13, 2026

作者: Kadir-Kaan Özer, René Ebeling, Markus Enzweiler

cs.AI

摘要

多元时间序列异常通常表现为跨通道依赖关系的变化，而非简单的幅度偏移。以自动驾驶为例，转向指令可能在内部保持一致性，但与实际产生的横向加速度形成解耦。当灵活的序列模型在协调关系改变后仍能合理重建信号时，基于残差的检测器往往会漏判此类异常。我们提出AxonAD——一种无监督检测器，将多头注意力查询向量的演化视为短时域可预测过程。该方法结合梯度更新的重建通路与纯历史预测器，后者通过过往上下文预测未来查询向量。训练采用带指数移动平均目标编码器的掩码预测目标函数。推理阶段将重建误差与尾部聚合查询失配分数相结合，该分数通过近期时间步的预测查询与目标查询之间的余弦偏差计算。这种双重策略在保持幅度级检测能力的同时，增强了对结构依赖关系变化的敏感性。在带区间标注的专有车载遥测数据以及TSB-AD多元基准套件（17个数据集、180个序列）上，采用无阈值和范围感知指标的实验表明，AxonAD在排序质量和时序定位方面均优于强基线模型。消融实验证实查询预测和组合评分是性能提升的主要驱动力。代码已发布于https://github.com/iis-esslingen/AxonAD。

English

Multivariate time series anomalies often manifest as shifts in cross-channel dependencies rather than simple amplitude excursions. In autonomous driving, for instance, a steering command might be internally consistent but decouple from the resulting lateral acceleration. Residual-based detectors can miss such anomalies when flexible sequence models still reconstruct signals plausibly despite altered coordination. We introduce AxonAD, an unsupervised detector that treats multi-head attention query evolution as a short horizon predictable process. A gradient-updated reconstruction pathway is coupled with a history-only predictor that forecasts future query vectors from past context. This is trained via a masked predictor-target objective against an exponential moving average (EMA) target encoder. At inference, reconstruction error is combined with a tail-aggregated query mismatch score, which measures cosine deviation between predicted and target queries on recent timesteps. This dual approach provides sensitivity to structural dependency shifts while retaining amplitude-level detection. On proprietary in-vehicle telemetry with interval annotations and on the TSB-AD multi-variate suite (17 datasets, 180 series) with threshold-free and range-aware metrics, AxonAD improves ranking quality and temporal localization over strong baselines. Ablations confirm that query prediction and combined scoring are the primary drivers of the observed gains. Code is available at the URL https://github.com/iis-esslingen/AxonAD.