# Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach

arXiv: https://arxiv.org/abs/1905.06484 · HTML: https://mlsanity.com/paper/1905.06484/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2019.

## Built on by (most cited first, 4 of 4)

- [Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey](https://mlsanity.com/paper/2203.00190/) (2022)
- [Voxel-wise Adversarial Semi-supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/2205.06987/) (2022)
- [STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification](https://mlsanity.com/paper/2108.08362/) (2021)
- [CS-UM6P at SemEval-2022 Task 6: Transformer-based Models for Intended Sarcasm Detection in English and Arabic](https://mlsanity.com/paper/2206.08415/) (2022)

## Abstract (arXiv)

Recently, semi-supervised learning methods based on generative adversarial networks (GANs) have received much attention. Among them, two distinct approaches have achieved competitive results on a variety of benchmark datasets. Bad GAN learns a classifier with unrealistic samples distributed on the complement of the support of the input data. Conversely, Triple GAN consists of a three-player game that tries to leverage good generated samples to boost classification results. In this paper, we perform a comprehensive comparison of these two approaches on different benchmark datasets. We demonstrate their different properties on image generation, and sensitivity to the amount of labeled data provided. By comprehensively comparing these two methods, we hope to shed light on the future of GAN-based semi-supervised learning.