# Studying Bias in GANs through the Lens of Race

arXiv: https://arxiv.org/abs/2209.02836 · HTML: https://mlsanity.com/paper/2209.02836/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 6 Sep 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [NIPS 2016 Tutorial: Generative Adversarial Networks](https://mlsanity.com/paper/1701.00160/) (2016)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (2019)
- [Towards a Critical Race Methodology in Algorithmic Fairness](https://mlsanity.com/paper/1912.03593/) (2019)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)
- [Megapixel Size Image Creation using Generative Adversarial Networks](https://mlsanity.com/paper/1706.00082/) (2017)
- [Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses](https://mlsanity.com/paper/2001.09528/) (2020)
- [Do GANs actually learn the distribution? An empirical study](https://mlsanity.com/paper/1706.08224/) (2017)
- [Prescribed Generative Adversarial Networks](https://mlsanity.com/paper/1910.04302/) (2019)
- [Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets](https://mlsanity.com/paper/2109.03229/) (2021)

## Built on by (most cited first, 30 of 31)

- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [ITI-GEN: Inclusive Text-to-Image Generation](https://mlsanity.com/paper/2309.05569/) (2023)
- [Balancing Act: Distribution-Guided Debiasing in Diffusion Models](https://mlsanity.com/paper/2402.18206/) (2024)
- [GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations](https://mlsanity.com/paper/2305.19962/) (2023)
- [Analyzing Bias in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2305.06402/) (2023)
- [Mass-Producing Failures of Multimodal Systems with Language Models](https://mlsanity.com/paper/2306.12105/) (2023)
- [MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading](https://mlsanity.com/paper/2312.13091/) (2023)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement](https://mlsanity.com/paper/2303.12059/) (2023)
- [How to Boost Face Recognition with StyleGAN?](https://mlsanity.com/paper/2210.10090/) (2022)
- [Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation](https://mlsanity.com/paper/2310.12583/) (2023)
- [On Measuring Fairness in Generative Models](https://mlsanity.com/paper/2310.19297/) (2023)
- [Gaussian Harmony: Attaining Fairness in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2312.14976/) (2023)
- [Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model](https://mlsanity.com/paper/2503.12536/) (2025)
- [Limitations of Face Image Generation](https://mlsanity.com/paper/2309.07277/) (2023)
- [Benchmarking the Fairness of Image Upsampling Methods](https://mlsanity.com/paper/2401.13555/) (2024)
- [Perceptual Fairness in Image Restoration](https://mlsanity.com/paper/2405.13805/) (2024)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model](https://mlsanity.com/paper/2402.09786/) (2024)
- [Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics](https://mlsanity.com/paper/2403.19897/) (2024)
- [Accuracy and Fairness of Facial Recognition Technology in Low-Quality Police Images: An Experiment With Synthetic Faces](https://mlsanity.com/paper/2505.14320/) (2025)
- [Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces](https://mlsanity.com/paper/2601.01082/) (2026)
- [BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling](https://mlsanity.com/paper/2603.01163/) (2026)
- [Fair GANs through model rebalancing for extremely imbalanced class distributions](https://mlsanity.com/paper/2308.08638/) (2023)
- [Sampling Strategies for Mitigating Bias in Face Synthesis Methods](https://mlsanity.com/paper/2405.11320/) (2024)
- [Mitigation of gender bias in automatic facial non-verbal behaviors generation](https://mlsanity.com/paper/2410.07274/) (2024)
- [GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension](https://mlsanity.com/paper/2604.09923/) (2026)
- [Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models](https://mlsanity.com/paper/2605.01185/) (2026)
- [Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands](https://mlsanity.com/paper/2607.09811/) (2026)
- [Position: Fairness Failure in Generative Models is an Evaluation Problem](https://mlsanity.com/paper/2608.16974/) (2026)

## Abstract (arXiv)

In this work, we study how the performance and evaluation of generative image models are impacted by the racial composition of their training datasets. By examining and controlling the racial distributions in various training datasets, we are able to observe the impacts of different training distributions on generated image quality and the racial distributions of the generated images. Our results show that the racial compositions of generated images successfully preserve that of the training data. However, we observe that truncation, a technique used to generate higher quality images during inference, exacerbates racial imbalances in the data. Lastly, when examining the relationship between image quality and race, we find that the highest perceived visual quality images of a given race come from a distribution where that race is well-represented, and that annotators consistently prefer generated images of white people over those of Black people.