Transformer-based models for anomaly detection in multivariate time series can benefit from the self-attention mechanism due to its advantage in modeling long-term dependencies. However, Transformer-based anomaly detection models have problems such as a large amount of data being required for training, standard positional encoding is not suitable for multivariate time series data, and the interdependence between time series is not considered. To address these limitations, we propose a novel anomaly detection method, named EdgeConvFormer, which integrates Time2vec embedding, stacked dynamic graph CNN, and Transformer to extract global and local spatial-time information. This design of EdgeConvFormer empowers it with decomposition capacities for complex time series, progressive spatiotemporal correlation discovery between time series, and representation aggregation of multi-scale features. Experiments demonstrate that EdgeConvFormer can learn the spatial-temporal correlations from multivariate time series data and achieve better anomaly detection performance than the state-of-the-art approaches on many real-world datasets of different scales.

翻译：基于Transformer的多变量时间序列异常检测模型可受益于自注意力机制在建模长期依赖关系方面的优势。然而，此类模型存在训练需大量数据、标准位置编码不适用于多变量时间序列数据，以及未考虑时间序列间相互依赖关系等问题。为解决上述局限，我们提出一种名为EdgeConvFormer的新型异常检测方法，该方法融合Time2vec嵌入、堆叠动态图CNN与Transformer，以提取全局与局部的时空信息。EdgeConvFormer的设计使其具备复杂时间序列分解、时间序列间渐进式时空关联发现以及多尺度特征表征聚合的能力。实验表明，EdgeConvFormer能从多变量时间序列数据中学习时空相关性，并在多个不同规模的真实数据集上取得优于现有最先进方法的异常检测性能。