EdgeConvFormer：基于动态图CNN和Transformer的多元时间序列异常检测
EdgeConvFormer: Dynamic Graph CNN and Transformer based Anomaly Detection in Multivariate Time Series
AI总结：
EdgeConvFormer通过结合Time2vec、动态图CNN和Transformer，解决Transformer异常检测中数据需求大、位置编码不适用及忽视序列间依赖的问题，并在多尺度真实数据集上实现更优的异常检测性能。
摘要：
基于Transformer的多元时间序列异常检测模型能够受益于自注意力机制，因为它在建模长期依赖关系方面具有优势。然而，基于Transformer的异常检测模型存在一些问题，例如训练需要大量数据、标准位置编码不适用于多元时间序列数据，以及未考虑时间序列之间的相互依赖关系。为了解决这些局限性，我们提出了一种新的异常检测方法，名为EdgeConvFormer，它集成了Time2vec嵌入、堆叠动态图CNN和Transformer，以提取全局和局部的时空信息。EdgeConvFormer的这种设计使其具备复杂时间序列的分解能力、时间序列之间渐进式时空相关性发现能力以及多尺度特征的表示聚合能力。实验表明，EdgeConvFormer能够从多元时间序列数据中学习时空相关性，并在许多不同规模的真实世界数据集上取得优于最先进方法的异常检测性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
