# Improving Correlation Capture in Generating Imbalanced Data using Differentially Private Conditional GANs

arXiv: https://arxiv.org/abs/2206.13787 · HTML: https://mlsanity.com/paper/2206.13787/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [DP-CGAN: Differentially Private Synthetic Data and Label Generation](https://mlsanity.com/paper/2001.09700/) (2020)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [Quant GANs: Deep Generation of Financial Time Series](https://mlsanity.com/paper/1907.06673/) (2019)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [Synthesizing Tabular Data using Generative Adversarial Networks](https://mlsanity.com/paper/1811.11264/) (2018)
- [Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning](https://mlsanity.com/paper/2008.09202/) (2020)
- [Differentially Private Synthetic Medical Data Generation using Convolutional GANs](https://mlsanity.com/paper/2012.11774/) (2020)
- [Differentially Private Synthetic Data: Applied Evaluations and Enhancements](https://mlsanity.com/paper/2011.05537/) (2020)
- [Synthetic Data for Social Good](https://mlsanity.com/paper/1710.08874/) (2017)
- [From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends](https://mlsanity.com/paper/2004.03586/) (2020)
- [Effective and Privacy preserving Tabular Data Synthesizing](https://mlsanity.com/paper/2108.10064/) (2021)

## Built on by (most cited first, 3 of 3)

- [Differential Privacy Under Class Imbalance: Methods and Empirical Insights](https://mlsanity.com/paper/2411.05733/) (2024)
- [zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation](https://mlsanity.com/paper/2410.20808/) (2024)
- [A Three-Way Knot: Privacy, Fairness, and Predictive Performance Dynamics](https://mlsanity.com/paper/2306.15567/) (2023)

## Abstract (arXiv)

Despite the remarkable success of Generative Adversarial Networks (GANs) on text, images, and videos, generating high-quality tabular data is still under development owing to some unique challenges such as capturing dependencies in imbalanced data, optimizing the quality of synthetic patient data while preserving privacy. In this paper, we propose DP-CGANS, a differentially private conditional GAN framework consisting of data transformation, sampling, conditioning, and networks training to generate realistic and privacy-preserving tabular data. DP-CGANS distinguishes categorical and continuous variables and transforms them to latent space separately. Then, we structure a conditional vector as an additional input to not only presents the minority class in the imbalanced data, but also capture the dependency between variables. We inject statistical noise to the gradients in the networking training process of DP-CGANS to provide a differential privacy guarantee. We extensively evaluate our model with state-of-the-art generative models on three public datasets and two real-world personal health datasets in terms of statistical similarity, machine learning performance, and privacy measurement. We demonstrate that our model outperforms other comparable models, especially in capturing dependency between variables. Finally, we present the balance between data utility and privacy in synthetic data generation considering the different data structure and characteristics of real-world datasets such as imbalance variables, abnormal distributions, and sparsity of data.