2017 MaximumLikelihoodAugmentedDiscr

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Maximum-Likelihood Augmented Discrete Generative Adversarial Network (MaliGAN), Generative Adversarial Network, Memory Augmented Neural Network.

Notes

Cited By

Quotes

Abstract

Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted. The fundamental reason is the difficulty of back-propagation through discrete random variables combined with the inherent instability of the GAN training objective. To address these problems, we propose Maximum-Likelihood Augmented Discrete Generative Adversarial Networks. Instead of directly optimizing the GAN objective, we derive a novel and low-variance objective using the discriminator's output that follows corresponds to the log-likelihood. Compared with the original, the new objective is proved to be consistent in theory and beneficial in practice. The experimental results on various discrete datasets demonstrate the effectiveness of the proposed approach.

References

BibTex

@article{2017_MaximumLikelihoodAugmentedDiscr,
  author    = {Tong Che and
               Yanran Li and
               Ruixiang Zhang and
               R. Devon Hjelm and
               Wenjie Li and
               Yangqiu Song and
 [[Yoshua Bengio]]},
  title     = {{Maximum-Likelihood Augmented Discrete Generative Adversarial Networks},
  journal   = {CoRR},
  volume    = {abs/1702.07983},
  year      = {2017},
  url       = {http://arxiv.org/abs/1702.07983},
  archivePrefix = {arXiv},
  eprint    = {1702.07983},
}


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2017 MaximumLikelihoodAugmentedDiscrYangqiu Song
Wenjie Li
Yoshua Bengio
Tong Che
Yanran Li
Ruixiang Zhang
R. Devon Hjelm
Maximum-Likelihood Augmented Discrete Generative Adversarial Networks2017