Periodic Graph-Enhanced Multivariate Time Series Anomaly Detector
By: Jia Li, Shiyu Long, Ye Yuan
Potential Business Impact:
Finds weird patterns in changing data.
Multivariate time series (MTS) anomaly detection commonly encounters in various domains like finance, healthcare, and industrial monitoring. However, existing MTS anomaly detection methods are mostly defined on the static graph structure, which fails to perform an accurate representation of complex spatio-temporal correlations in MTS. To address this issue, this study proposes a Periodic Graph-Enhanced Multivariate Time Series Anomaly Detector (PGMA) with the following two-fold ideas: a) designing a periodic time-slot allocation strategy based Fast Fourier Transform (FFT), which enables the graph structure to reflect dynamic changes in MTS; b) utilizing graph neural network and temporal extension convolution to accurate extract the complex spatio-temporal correlations from the reconstructed periodic graphs. Experiments on four real datasets from real applications demonstrate that the proposed PGMA outperforms state-of-the-art models in MTS anomaly detection.
Similar Papers
MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification
Machine Learning (CS)
Finds patterns in changing data for better predictions.
Continuous Wavelet Transform and Siamese Network-Based Anomaly Detection in Multi-variate Semiconductor Process Time Series
Machine Learning (CS)
Finds tiny problems in chip making early.
Transformer-based Multivariate Time Series Anomaly Localization
Machine Learning (CS)
Finds problems in smart systems faster.