Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detection
This work addresses anomaly detection in time series for domains like finance and healthcare, offering an incremental advance by incorporating spatial information into existing temporal models.
The paper tackles the problem of time series anomaly detection by proposing a novel spatial-temporal normality learning approach (STEN) that combines temporal and spatial modules, achieving substantial performance improvements over state-of-the-art methods on five benchmarks.
Time Series Anomaly Detection (TSAD) finds widespread applications across various domains such as financial markets, industrial production, and healthcare. Its primary objective is to learn the normal patterns of time series data, thereby identifying deviations in test samples. Most existing TSAD methods focus on modeling data from the temporal dimension, while ignoring the semantic information in the spatial dimension. To address this issue, we introduce a novel approach, called Spatial-Temporal Normality learning (STEN). STEN is composed of a sequence Order prediction-based Temporal Normality learning (OTN) module that captures the temporal correlations within sequences, and a Distance prediction-based Spatial Normality learning (DSN) module that learns the relative spatial relations between sequences in a feature space. By synthesizing these two modules, STEN learns expressive spatial-temporal representations for the normal patterns hidden in the time series data. Extensive experiments on five popular TSAD benchmarks show that STEN substantially outperforms state-of-the-art competing methods. Our code is available at https://github.com/mala-lab/STEN.