Good Semi-supervised Learning That Requires a Bad GAN
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 semi-supervised 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.
BibTeX
@inproceedings{NIPS2017_79514e88,
author = {Dai, Zihang and Yang, Zhilin and Yang, Fan and Cohen, William W and Salakhutdinov, Russ R},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Good Semi-supervised Learning That Requires a Bad GAN},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/79514e888b8f2acacc68738d0cbb803e-Paper.pdf},
volume = {30},
year = {2017}
}