EdgeConvFormer: Dynamic Graph CNN and Transformer based Anomaly Detection in Multivariate Time Series
This work addresses anomaly detection for multivariate time series data, offering an incremental improvement by combining existing techniques to enhance spatial-temporal correlation modeling.
The paper tackles anomaly detection in multivariate time series by proposing EdgeConvFormer, which integrates Time2vec embedding, dynamic graph CNN, and Transformer to address limitations like training data requirements and lack of interdependence modeling, achieving better performance than state-of-the-art methods on real-world datasets.
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.