Semi-Supervised Learning with Generative Adversarial Networks

2016/06/05 by Odena, Augustus · 5 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1606.01583

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.

Cited by

• BeHGAN: Bengali Handwritten Word Generation from Plain Text Using Generative Adversarial Networks
• Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy
• SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation
• Masked Conditioning for Deep Generative Models
• Physics-Guided Multi-View Graph Neural Network for Schizophrenia Classification via Structural-Functional Coupling

Related

• How Does GAN-based Semi-supervised Learning Work?
• Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Good Semi-supervised Learning that Requires a Bad GAN
• Semi-supervised Learning using Adversarial Training with Good and Bad Samples