# Improving the quality of generative models through Smirnov transformation

arXiv: https://arxiv.org/abs/2110.15914 · HTML: https://mlsanity.com/paper/2110.15914/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Are GANs Created Equal? A Large-Scale Study](https://mlsanity.com/paper/1711.10337/) (2017)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Stabilizing Training of Generative Adversarial Networks through Regularization](https://mlsanity.com/paper/1705.09367/) (2017)
- [A Survey on Generative Adversarial Networks: Variants, Applications, and Training](https://mlsanity.com/paper/2006.05132/) (2020)
- [How good is my GAN?](https://mlsanity.com/paper/1807.09499/) (2018)
- [Amortised MAP Inference for Image Super-resolution](https://mlsanity.com/paper/1610.04490/) (2016)
- [Gradient descent GAN optimization is locally stable](https://mlsanity.com/paper/1706.04156/) (2017)
- [Geometry Score: A Method For Comparing Generative Adversarial Networks](https://mlsanity.com/paper/1802.02664/) (2018)
- [IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection](https://mlsanity.com/paper/1809.02077/) (2018)
- [Generative Adversarial Networks for Spatio-temporal Data: A Survey](https://mlsanity.com/paper/2008.08903/) (2020)
- [Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation](https://mlsanity.com/paper/2105.04184/) (2021)
- [Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks](https://mlsanity.com/paper/2107.14776/) (2021)

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

- [Data Augmentation techniques in time series domain: A survey and taxonomy](https://mlsanity.com/paper/2206.13508/) (2022)

## Abstract (arXiv)

Solving the convergence issues of Generative Adversarial Networks (GANs) is one of the most outstanding problems in generative models. In this work, we propose a novel activation function to be used as output of the generator agent. This activation function is based on the Smirnov probabilistic transformation and it is specifically designed to improve the quality of the generated data. In sharp contrast with previous works, our activation function provides a more general approach that deals not only with the replication of categorical variables but with any type of data distribution (continuous or discrete). Moreover, our activation function is derivable and therefore, it can be seamlessly integrated in the backpropagation computations during the GAN training processes. To validate this approach, we evaluate our proposal against two different data sets: a) an artificially rendered data set containing a mixture of discrete and continuous variables, and b) a real data set of flow-based network traffic data containing both normal connections and cryptomining attacks. To evaluate the fidelity of the generated data, we analyze both their results in terms of quality measures of statistical nature and also regarding the use of these synthetic data to feed a nested machine learning-based classifier. The experimental results evince a clear outperformance of the GAN network tuned with this new activation function with respect to both a na"ive mean-based generator and a standard GAN. The quality of the data is so high that the generated data can fully substitute real data for training the nested classifier without a fall in the obtained accuracy. This result encourages the use of GANs to produce high-quality synthetic data that are applicable in scenarios in which data privacy must be guaranteed.