Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series
This work addresses a specific evaluation problem for researchers using GANs in multivariate time series generation, but it appears incremental as it builds on existing statistical tests and visualization methods.
The authors tackled the challenge of visually evaluating GAN-generated multivariate time series by proposing a framework called Gaussian GANs, which uses the GAN itself as a transformation function in a normality test, and they demonstrated its effectiveness on the UniMiB dataset with empirical evidence.
Visually evaluating the goodness of generated Multivariate Time Series (MTS) are difficult to implement, especially in the case that the generative model is Generative Adversarial Networks (GANs). We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS generation task. Firstly, we attempt to find the transformation function in the multivariate Kolmogorov Smirnov (MKS) test by explicitly reconstructing the architecture of GANs. Secondly, we conduct the normality test of transformed MST where the Gaussian GANs serves as the transformation function in the MKS test. In order to simplify the normality test, an efficient visualization is proposed using the chi square distribution. In the experiment, we use the UniMiB dataset and provide empirical evidence showing that the normality test using Gaussian GANs and chi sqaure visualization is effective and credible.