# On the Fairness of Generative Adversarial Networks (GANs)

arXiv: https://arxiv.org/abs/2103.00950 · HTML: https://mlsanity.com/paper/2103.00950/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 1 Mar 2021.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (2019)
- [C-RNN-GAN: Continuous recurrent neural networks with adversarial training](https://mlsanity.com/paper/1611.09904/) (2016)
- [Long Text Generation via Adversarial Training with Leaked Information](https://mlsanity.com/paper/1709.08624/) (2017)
- [BAGAN: Data Augmentation with Balancing GAN](https://mlsanity.com/paper/1803.09655/) (2018)
- [Data Augmentation Using GANs](https://mlsanity.com/paper/1904.09135/) (2019)
- [Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.04357/) (2016)
- [Learning Fair Representations via an Adversarial Framework](https://mlsanity.com/paper/1904.13341/) (2019)
- [Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation](https://mlsanity.com/paper/2010.05119/) (2020)
- [Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks](https://mlsanity.com/paper/1709.01421/) (2017)

## Built on by (most cited first, 14 of 14)

- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias](https://mlsanity.com/paper/2403.07857/) (2024)
- [Fair Sampling in Diffusion Models through Switching Mechanism](https://mlsanity.com/paper/2401.03140/) (2024)
- [RepFair-GAN: Mitigating Representation Bias in GANs Using Gradient Clipping](https://mlsanity.com/paper/2207.10653/) (2022)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model](https://mlsanity.com/paper/2503.12536/) (2025)
- [Adversarial Stacked Auto-Encoders for Fair Representation Learning](https://mlsanity.com/paper/2107.12826/) (2021)
- [Fairness in generative modeling](https://mlsanity.com/paper/2210.03517/) (2022)
- [Balanced Face Dataset: Guiding StyleGAN to Generate Labeled Synthetic Face Image Dataset for Underrepresented Group](https://mlsanity.com/paper/2308.03495/) (2023)
- [Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learning](https://mlsanity.com/paper/2402.07586/) (2024)
- [Downstream Fairness Caveats with Synthetic Healthcare Data](https://mlsanity.com/paper/2203.04462/) (2022)
- [STEB: In Search of the Best Evaluation Approach for Synthetic Time Series](https://mlsanity.com/paper/2505.21160/) (2025)
- [Fair GANs through model rebalancing for extremely imbalanced class distributions](https://mlsanity.com/paper/2308.08638/) (2023)
- [The Benefits and Risks of Transductive Approaches for AI Fairness](https://mlsanity.com/paper/2406.12011/) (2024)

## Abstract (arXiv)

Generative adversarial networks (GANs) are one of the greatest advances in AI in recent years. With their ability to directly learn the probability distribution of data, and then sample synthetic realistic data. Many applications have emerged, using GANs to solve classical problems in machine learning, such as data augmentation, class unbalance problems, and fair representation learning. In this paper, we analyze and highlight fairness concerns of GANs model. In this regard, we show empirically that GANs models may inherently prefer certain groups during the training process and therefore they're not able to homogeneously generate data from different groups during the testing phase. Furthermore, we propose solutions to solve this issue by conditioning the GAN model towards samples' group or using ensemble method (boosting) to allow the GAN model to leverage distributed structure of data during the training phase and generate groups at equal rate during the testing phase.