GAN-Based Anomaly Detection for Multivariate Time Series Using Polluted Training Set

Multivariate time series anomaly detection has great potentials in many practical applications such as structural health monitoring, intelligent operation and maintenance, quantitative trading, etc. Extreme unbalanced training set and noise interference make it challenging to accurately capture the distribution of normal data and then detect anomalies. Recently, dozens of AutoEncoder (AE) and Generative Adversarial Network (GAN) based methods have been proposed to learn the latent representation of normal data and then detect anomalies based on reconstruction error. However, existing AE-based approaches are lack of effective regularization method specially designed for anomaly detection tasks thus easily overfitting while GAN-based approaches are mostly trained under the hypothesis of pollution-free training set, which means the training set is all composed of normal samples and that is hard to satisfy in practice. To tackle these problems, in this paper we propose a GAN based anomaly detection method for multivariate time series named FGANomaly (letter F is for Filter). The core idea is to filter possible anomalous samples with pseudo-labels before training the discriminator thus to capture the distribution of normal data as precise as possible. In addition, we design a novel training objective for the generator, which leads the generator to concentrate more on plausible normal data and ignore anomalies. We conducted comprehensive experiments on four public datasets, and the experimental results show the superiority of our method over baselines in both performance and robustness.