English

Semi-Supervised Learning with Generative Adversarial Networks

Machine Learning 2016-10-25 v2 Machine Learning

Abstract

We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N classes. At training time, D is made to predict which of N+1 classes the input belongs to, where an extra class is added to correspond to the outputs of G. We show that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.

Keywords

Cite

@article{arxiv.1606.01583,
  title  = {Semi-Supervised Learning with Generative Adversarial Networks},
  author = {Augustus Odena},
  journal= {arXiv preprint arXiv:1606.01583},
  year   = {2016}
}

Comments

Appearing in the Data Efficient Machine Learning workshop at ICML 2016

R2 v1 2026-06-22T14:18:15.993Z