Boundary-Seeking Generative Adversarial Networks
Abstract
Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator. The importance weights have a strong connection to the decision boundary of the discriminator, and we call our method boundary-seeking GANs (BGANs). We demonstrate the effectiveness of the proposed algorithm with discrete image and character-based natural language generation. In addition, the boundary-seeking objective extends to continuous data, which can be used to improve stability of training, and we demonstrate this on Celeba, Large-scale Scene Understanding (LSUN) bedrooms, and Imagenet without conditioning.
Cite
@article{arxiv.1702.08431,
title = {Boundary-Seeking Generative Adversarial Networks},
author = {R Devon Hjelm and Athul Paul Jacob and Tong Che and Adam Trischler and Kyunghyun Cho and Yoshua Bengio},
journal= {arXiv preprint arXiv:1702.08431},
year = {2018}
}