# Semi-Supervised Learning with GANs: Revisiting Manifold Regularization

arXiv: https://arxiv.org/abs/1805.08957 · HTML: https://mlsanity.com/paper/1805.08957/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

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

- [Learning Globally Smooth Functions on Manifolds](https://mlsanity.com/paper/2210.00301/) (2022)
- [Taming Overconfident Prediction on Unlabeled Data from Hindsight](https://mlsanity.com/paper/2112.08200/) (2021)
- [Deep Invertible Approximation of Topologically Rich Maps between Manifolds](https://mlsanity.com/paper/2210.00577/) (2022)
- [Training Image Derivatives: Increased Accuracy and Universal Robustness](https://mlsanity.com/paper/2310.14045/) (2023)

## Abstract (arXiv)

GANS are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating the Laplacian norm using a Monte Carlo approximation that is easily computed with the GAN. When incorporated into the feature-matching GAN of Improved GAN, we achieve state-of-the-art results for GAN-based semi-supervised learning on the CIFAR-10 dataset, with a method that is significantly easier to implement than competing methods.