Good Semi-supervised Learning that Requires a Bad GAN [article]

Zihang Dai, Zhilin Yang, Fan Yang, William W. Cohen, Ruslan Salakhutdinov
2017 arXiv   pre-print
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
more » ... r. 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.
arXiv:1705.09783v3 fatcat:y572pefrz5bcflp3nhbxkilewm