papers AI Learner
The Github is limit! Click to go to the new site.

Good Semi-supervised Learning that Requires a Bad GAN

2017-11-03
Zihang Dai, Zhilin Yang, Fan Yang, William W. Cohen, Ruslan Salakhutdinov

Abstract

Semi-supervised learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why good semi-supervised classification performance and a good generator cannot be obtained at the same time. Theoretically, we show that given the discriminator objective, good semisupervised learning indeed requires a bad generator, and propose the definition of a preferred generator. Empirically, we derive a novel formulation based on our analysis that substantially improves over feature matching GANs, obtaining state-of-the-art results on multiple benchmark datasets.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1705.09783

PDF

https://arxiv.org/pdf/1705.09783


Similar Posts

下一篇 Fisher GAN

Comments