QRGAN: Quantile Regression Generative Adversarial Networks

Sunyeop Lee, Tuan Anh Nguyen, Dugki Min

Keywords: Quantile Regression, Generative Adversarial Networks (GANs), Frechet Inception Distance (FID), Generative Neural Networks

Abstract: Learning high-dimensional probability distributions by competitively training generative and discriminative neural networks is a prominent approach of Generative Adversarial Networks (GANs) among generative models to model complex real-world data. Nevertheless, training GANs likely suffer from non-convergence problem, mode collapse and gradient explosion or vanishing. Least Squares GAN (LSGANs) and Wasserstein GANs (WGAN) are of representative variants of GANs in literature that diminish the inherent problems of GANs by proposing the modification methodology of loss functions. However, LSGANs often fall into local minima and cause mode collapse. While WGANs unexpectedly encounter with inefficient computation and slow training due to its constraints in Wasserstein distance approximation. In this paper, we propose Quantile Regression GAN (QRGAN) in which quantile regression is adopted to minimize 1-Wasserstein distance between real and generated data distribution as a novel approach in modification of loss functions for improvement of GANs. To study the culprits of mode collapse problem, the output space of discriminator and gradients of fake samples are analyzed to see if the discriminator guides the generator well. And we found that the discriminator should not be bounded to specific numbers. Our proposed QRGAN exposes high robustness against mode collapse problem. Furthermore, QRGAN obtains an apparent improvement in the evaluation and comparison of Frechet Inception Distance (FID) for generation performance assessment compared to existing variants of GANs.

One-sentence Summary: A novel generative adversarial network with quantile regression for a significant improvement of model robustness and generation performance

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=lCp4a0xxVU