Anomaly detection with Wasserstein GAN

TL;DR

This paper explores using Wasserstein GANs with encoders for anomaly detection in time series data, achieving state-of-the-art results on MNIST and extending to multivariate time series.

Contribution

It introduces a novel approach combining Wasserstein GANs with encoders for effective anomaly detection in time series datasets.

Findings

W-GAN with encoder outperforms existing methods on MNIST.

The approach is extended to multivariate time series data.

State-of-the-art anomaly detection scores are achieved.

Abstract

Generative adversarial networks are a class of generative algorithms that have been widely used to produce state-of-the-art samples. In this paper, we investigate GAN to perform anomaly detection on time series dataset. In order to achieve this goal, a bibliography is made focusing on theoretical properties of GAN and GAN used for anomaly detection. A Wasserstein GAN has been chosen to learn the representation of normal data distribution and a stacked encoder with the generator performs the anomaly detection. W-GAN with encoder seems to produce state of the art anomaly detection scores on MNIST dataset and we investigate its usage on multi-variate time series.