# zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation

arXiv: https://arxiv.org/abs/2410.20808 · HTML: https://mlsanity.com/paper/2410.20808/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Builds on (most cited first, 17 of 17)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning](https://mlsanity.com/paper/2106.02584/) (2021)
- [Synthesizing Tabular Data using Generative Adversarial Networks](https://mlsanity.com/paper/1811.11264/) (2018)
- [PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series](https://mlsanity.com/paper/2108.00981/) (2021)
- [G2D: Generate to Detect Anomaly](https://mlsanity.com/paper/2006.11629/) (2020)
- [Feature Importance Estimation with Self-Attention Networks](https://mlsanity.com/paper/2002.04464/) (2020)
- [FCT-GAN: Enhancing Table Synthesis via Fourier Transform](https://mlsanity.com/paper/2210.06239/) (2022)
- [GAN-based Tabular Data Generator for Constructing Synopsis in Approximate Query Processing: Challenges and Solutions](https://mlsanity.com/paper/2212.09015/) (2022)
- [Rethinking Self-Attention: Towards Interpretability in Neural Parsing](https://mlsanity.com/paper/1911.03875/) (2019)
- [Improving Correlation Capture in Generating Imbalanced Data using Differentially Private Conditional GANs](https://mlsanity.com/paper/2206.13787/) (2022)
- [STING: Self-attention based Time-series Imputation Networks using GAN](https://mlsanity.com/paper/2209.10801/) (2022)
- [Tailoring Generative Adversarial Networks for Smooth Airfoil Design](https://mlsanity.com/paper/2404.11816/) (2024)
- [A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approaches](https://mlsanity.com/paper/2405.16971/) (2024)
- [A self-attention-based differentially private tabular GAN with high data utility](https://mlsanity.com/paper/2312.13031/) (2023)

## Built on by (most cited first, 2 of 2)

- [Hellinger loss function for Generative Adversarial Networks](https://mlsanity.com/paper/2512.12267/) (2025)
- [TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement](https://mlsanity.com/paper/2608.11951/) (2026)

## Abstract (arXiv)

The phenomenon of "black swans" has posed a fundamental challenge to performance of classical machine learning models. The perceived rise in frequency of outlier conditions, especially in post-pandemic environment, has necessitated exploration of synthetic data as a complement to real data in model training. This article provides a general overview and experimental investigation of the zGAN model architecture developed for the purpose of generating synthetic tabular data with outlier characteristics. The model is put to test in binary classification environments and shows promising results on realistic synthetic data generation, as well as uplift capabilities vis-`a-vis model performance. A distinctive feature of zGAN is its enhanced correlation capability between features in the generated data, replicating correlations of features in real training data. Furthermore, crucial is the ability of zGAN to generate outliers based on covariance of real data or synthetically generated covariances. This approach to outlier generation enables modeling of complex economic events and augmentation of outliers for tasks such as training predictive models and detecting, processing or removing outliers. Experiments and comparative analyses as part of this study were conducted on both private (credit risk in financial services) and public datasets.