Generative Adversarial Network (GAN) models have shown to be effective in a wide range of machine learning applications,and tabular data generation process has not been an exception. GANBLR is a new state-of-the-art tabular generation model. It uses the Bayesian Network as the generator which is trained adversarially against the discriminator. The GANBLR can not only address the interpretation limitation in existing tabular GAN-based models but can provide capability to handle explicit feature interactions.
Source: PAKDD Tutorial