# RepFair-GAN: Mitigating Representation Bias in GANs Using Gradient Clipping

arXiv: https://arxiv.org/abs/2207.10653 · HTML: https://mlsanity.com/paper/2207.10653/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 13 Jul 2022.

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

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [A Critical Review of Recurrent Neural Networks for Sequence Learning](https://mlsanity.com/paper/1506.00019/) (2015)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [Fair Generative Modeling via Weak Supervision](https://mlsanity.com/paper/1910.12008/) (2019)
- [BAGAN: Data Augmentation with Balancing GAN](https://mlsanity.com/paper/1803.09655/) (2018)
- [Data Augmentation Using GANs](https://mlsanity.com/paper/1904.09135/) (2019)
- [Improving the Fairness of Deep Generative Models without Retraining](https://mlsanity.com/paper/2012.04842/) (2020)
- [On the Fairness of Generative Adversarial Networks (GANs)](https://mlsanity.com/paper/2103.00950/) (2021)
- [Adversarial Stacked Auto-Encoders for Fair Representation Learning](https://mlsanity.com/paper/2107.12826/) (2021)

## Built on by (most cited first, 9 of 9)

- [ITI-GEN: Inclusive Text-to-Image Generation](https://mlsanity.com/paper/2309.05569/) (2023)
- [OpenBias: Open-set Bias Detection in Text-to-Image Generative Models](https://mlsanity.com/paper/2404.07990/) (2024)
- [Analyzing Bias in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2305.06402/) (2023)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Survey on AI Ethics: A Socio-technical Perspective](https://mlsanity.com/paper/2311.17228/) (2023)
- [GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2408.16700/) (2024)
- [Fair GANs through model rebalancing for extremely imbalanced class distributions](https://mlsanity.com/paper/2308.08638/) (2023)
- [AGGC: Adaptive Group Gradient Clipping for Stabilizing Large Language Model Training](https://mlsanity.com/paper/2601.11864/) (2026)

## Abstract (arXiv)

Fairness has become an essential problem in many domains of Machine Learning (ML), such as classification, natural language processing, and Generative Adversarial Networks (GANs). In this research effort, we study the unfairness of GANs. We formally define a new fairness notion for generative models in terms of the distribution of generated samples sharing the same protected attributes (gender, race, etc.). The defined fairness notion (representational fairness) requires the distribution of the sensitive attributes at the test time to be uniform, and, in particular for GAN model, we show that this fairness notion is violated even when the dataset contains equally represented groups, i.e., the generator favors generating one group of samples over the others at the test time. In this work, we shed light on the source of this representation bias in GANs along with a straightforward method to overcome this problem. We first show on two widely used datasets (MNIST, SVHN) that when the norm of the gradient of one group is more important than the other during the discriminator's training, the generator favours sampling data from one group more than the other at test time. We then show that controlling the groups' gradient norm by performing group-wise gradient norm clipping in the discriminator during the training leads to a more fair data generation in terms of representational fairness compared to existing models while preserving the quality of generated samples.