# Measuring Fairness in Generative Models

arXiv: https://arxiv.org/abs/2107.07754 · HTML: https://mlsanity.com/paper/2107.07754/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 16 Jul 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [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)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Fair Generative Modeling via Weak Supervision](https://mlsanity.com/paper/1910.12008/) (2019)
- [Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting](https://mlsanity.com/paper/1906.09531/) (2019)
- [A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection](https://mlsanity.com/paper/2103.17195/) (2021)
- [Improving the Fairness of Deep Generative Models without Retraining](https://mlsanity.com/paper/2012.04842/) (2020)
- [Dist-GAN: An Improved GAN using Distance Constraints](https://mlsanity.com/paper/1803.08887/) (2018)
- [Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game](https://mlsanity.com/paper/1911.06997/) (2019)

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

- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)
- [Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases](https://mlsanity.com/paper/2303.05470/) (2023)
- [AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark](https://mlsanity.com/paper/2406.00783/) (2024)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [Label-Only Model Inversion Attacks via Knowledge Transfer](https://mlsanity.com/paper/2310.19342/) (2023)
- [EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Models](https://mlsanity.com/paper/2303.05656/) (2023)
- [SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP](https://mlsanity.com/paper/2408.10202/) (2024)
- [Exploring Bias in over 100 Text-to-Image Generative Models](https://mlsanity.com/paper/2503.08012/) (2025)
- [On Measuring Fairness in Generative Models](https://mlsanity.com/paper/2310.19297/) (2023)
- [FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation](https://mlsanity.com/paper/2410.18615/) (2024)
- [FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models](https://mlsanity.com/paper/2510.21363/) (2025)
- [Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance](https://mlsanity.com/paper/2503.04736/) (2025)
- [Fit for Purpose? Deepfake Detection in the Real World](https://mlsanity.com/paper/2510.16556/) (2025)
- [A Comprehensive Survey and Classification of Evaluation Criteria for Trustworthy Artificial Intelligence](https://mlsanity.com/paper/2410.17281/) (2024)
- [Data Pruning in Generative Diffusion Models](https://mlsanity.com/paper/2411.12523/) (2024)
- [Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models](https://mlsanity.com/paper/2509.22723/) (2025)
- [Fairness in generative modeling](https://mlsanity.com/paper/2210.03517/) (2022)
- [On the Fairness, Diversity and Reliability of Text-to-Image Generative Models](https://mlsanity.com/paper/2411.13981/) (2024)
- [On Optimal Steering to Achieve Exact Fairness](https://mlsanity.com/paper/2509.15759/) (2025)
- [AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation](https://mlsanity.com/paper/2406.12805/) (2024)
- [Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models](https://mlsanity.com/paper/2602.08660/) (2026)
- [HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing](https://mlsanity.com/paper/2605.24687/) (2026)
- [Fair GANs through model rebalancing for extremely imbalanced class distributions](https://mlsanity.com/paper/2308.08638/) (2023)
- [Text-to-Image Representativity Fairness Evaluation Framework](https://mlsanity.com/paper/2410.14201/) (2024)
- [Improving Fairness in LLMs Through Testing-Time Adversaries](https://mlsanity.com/paper/2505.12100/) (2025)
- [Fairness risk and its privacy-enabled solution in AI-driven robotic applications](https://mlsanity.com/paper/2601.08953/) (2026)
- [Disparate Impact in Synthetic Data Generation](https://mlsanity.com/paper/2606.13105/) (2026)
- [Position: Fairness Failure in Generative Models is an Evaluation Problem](https://mlsanity.com/paper/2608.16974/) (2026)

## Abstract (arXiv)

Deep generative models have made much progress in improving training stability and quality of generated data. Recently there has been increased interest in the fairness of deep-generated data. Fairness is important in many applications, e.g. law enforcement, as biases will affect efficacy. Central to fair data generation are the fairness metrics for the assessment and evaluation of different generative models. In this paper, we first review fairness metrics proposed in previous works and highlight potential weaknesses. We then discuss a performance benchmark framework along with the assessment of alternative metrics.