Correlated discrete data generation using adversarial training
It addresses a specific problem in generative modeling for discrete data, which is incremental as it builds on existing GAN methods.
The paper tackled the challenge of generating discrete data by proposing an adversarial training-based model for correlated discrete data generation, showing it performs better than an existing model that overlooks correlation on datasets like job-seeking candidates skill set and MNIST.
Generative Adversarial Networks (GAN) have shown great promise in tasks like synthetic image generation, image inpainting, style transfer, and anomaly detection. However, generating discrete data is a challenge. This work presents an adversarial training based correlated discrete data (CDD) generation model. It also details an approach for conditional CDD generation. The results of our approach are presented over two datasets; job-seeking candidates skill set (private dataset) and MNIST (public dataset). From quantitative and qualitative analysis of these results, we show that our model performs better as it leverages inherent correlation in the data, than an existing model that overlooks correlation.