MGADN: A Multi-task Graph Anomaly Detection Network for Multivariate Time Series
This work addresses anomaly detection for multivariate time series in domains like sensor networks, but it appears incremental as it builds on existing graph neural network and LSTM techniques.
The paper tackles the problem of detecting anomalies in multivariate time series by addressing the limitations of existing methods that only consider temporal relationships or rely on single-model approaches, proposing a multi-task graph anomaly detection network that combines prediction and reconstruction models, achieving unspecified performance improvements.
Anomaly detection of time series, especially multivariate time series(time series with multiple sensors), has been focused on for several years. Though existing method has achieved great progress, there are several challenging problems to be solved. Firstly, existing method including neural network only concentrate on the relationship in terms of timestamp. To be exact, they only want to know how does the data in the past influence which in the future. However, one sensor sometimes intervenes in other sensor such as the speed of wind may cause decrease of temperature. Secondly, there exist two categories of model for time series anomaly detection: prediction model and reconstruction model. Prediction model is adept at learning timely representation while short of capability when faced with sparse anomaly. Conversely, reconstruction model is opposite. Therefore, how can we efficiently get the relationship both in terms of both timestamp and sensors becomes our main topic. Our approach uses GAT, which is originated from graph neural network, to obtain connection between sensors. And LSTM is used to obtain relationships timely. Our approach is also designed to be double headed to calculate both prediction loss and reconstruction loss via VAE(Variational Auto-Encoder). In order to take advantage of two sorts of model, multi-task optimization algorithm is used in this model.