# Universum GANs: Improving GANs through contradictions

arXiv: https://arxiv.org/abs/2106.09946 · HTML: https://mlsanity.com/paper/2106.09946/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 18 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [An Overview of Deep Semi-Supervised Learning](https://mlsanity.com/paper/2006.05278/) (2020)
- [Good Semi-supervised Learning that Requires a Bad GAN](https://mlsanity.com/paper/1705.09783/) (2017)
- [Auxiliary Deep Generative Models](https://mlsanity.com/paper/1602.05473/) (2016)
- [Triple Generative Adversarial Nets](https://mlsanity.com/paper/1703.02291/) (2017)
- [Universum Prescription: Regularization using Unlabeled Data](https://mlsanity.com/paper/1511.03719/) (2015)
- [Transductive Label Augmentation for Improved Deep Network Learning](https://mlsanity.com/paper/1805.10546/) (2018)
- [Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning](https://mlsanity.com/paper/1911.02522/) (2019)
- [DOC3-Deep One Class Classification using Contradictions](https://mlsanity.com/paper/2105.07636/) (2021)
- [Large Margin Semi-supervised Structured Output Learning](https://mlsanity.com/paper/1311.2139/) (2013)

## Built on by (most cited first, 1 of 1)

- [Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples](https://mlsanity.com/paper/2309.16143/) (2023)

## Abstract (arXiv)

Limited availability of labeled-data makes any supervised learning problem challenging. Alternative learning settings like semi-supervised and universum learning alleviate the dependency on labeled data, but still require a large amount of unlabeled data, which may be unavailable or expensive to acquire. GAN-based data generation methods have recently shown promise by generating synthetic samples to improve learning. However, most existing GAN based approaches either provide poor discriminator performance under limited labeled data settings; or results in low quality generated data. In this paper, we propose a Universum GAN game which provides improved discriminator accuracy under limited data settings, while generating high quality realistic data. We further propose an evolving discriminator loss which improves its convergence and generalization performance. We derive the theoretical guarantees and provide empirical results in support of our approach.