# Improving the Fairness of Deep Generative Models without Retraining

arXiv: https://arxiv.org/abs/2012.04842 · HTML: https://mlsanity.com/paper/2012.04842/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 30 of 46)

- [Generative Models as a Data Source for Multiview Representation Learning](https://mlsanity.com/paper/2106.05258/) (2021)
- [Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis](https://mlsanity.com/paper/2208.13753/) (2022)
- [Intermediate Layer Optimization for Inverse Problems using Deep Generative Models](https://mlsanity.com/paper/2102.07364/) (2021)
- [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)
- [Balancing Act: Distribution-Guided Debiasing in Diffusion Models](https://mlsanity.com/paper/2402.18206/) (2024)
- [Analyzing Bias in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2305.06402/) (2023)
- [T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation](https://mlsanity.com/paper/2306.00905/) (2023)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)
- [Fairness for Image Generation with Uncertain Sensitive Attributes](https://mlsanity.com/paper/2106.12182/) (2021)
- [Measuring Fairness in Generative Models](https://mlsanity.com/paper/2107.07754/) (2021)
- [Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models](https://mlsanity.com/paper/2209.06970/) (2022)
- [Fair Generative Models via Transfer Learning](https://mlsanity.com/paper/2212.00926/) (2022)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining](https://mlsanity.com/paper/2110.08009/) (2021)
- [Region-Based Semantic Factorization in GANs](https://mlsanity.com/paper/2202.09649/) (2022)
- [FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations](https://mlsanity.com/paper/2202.06240/) (2022)
- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [Data Redaction from Pre-trained GANs](https://mlsanity.com/paper/2206.14389/) (2022)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [RepFair-GAN: Mitigating Representation Bias in GANs Using Gradient Clipping](https://mlsanity.com/paper/2207.10653/) (2022)
- [Uncovering Bias in Face Generation Models](https://mlsanity.com/paper/2302.11562/) (2023)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [On Measuring Fairness in Generative Models](https://mlsanity.com/paper/2310.19297/) (2023)
- [Disentangling and Operationalizing AI Fairness at LinkedIn](https://mlsanity.com/paper/2306.00025/) (2023)
- [Self-Conditioned Generative Adversarial Networks for Image Editing](https://mlsanity.com/paper/2202.04040/) (2022)
- [Training Class-Imbalanced Diffusion Model Via Overlap Optimization](https://mlsanity.com/paper/2402.10821/) (2024)
- [Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling](https://mlsanity.com/paper/2212.02090/) (2022)
- [Gaussian Harmony: Attaining Fairness in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2312.14976/) (2023)
- [Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations](https://mlsanity.com/paper/2405.19201/) (2024)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due to a biased image generation process. To study the issue, we first conduct an empirical study on a pre-trained face synthesis model. We observe that after training the GAN model not only carries the biases in the training data but also amplifies them to some degree in the image generation process. To further improve the fairness of image generation, we propose an interpretable baseline method to balance the output facial attributes without retraining. The proposed method shifts the interpretable semantic distribution in the latent space for a more balanced image generation while preserving the sample diversity. Besides producing more balanced data regarding a particular attribute (e.g., race, gender, etc.), our method is generalizable to handle more than one attribute at a time and synthesize samples of fine-grained subgroups. We further show the positive applicability of the balanced data sampled from GANs to quantify the biases in other face recognition systems, like commercial face attribute classifiers and face super-resolution algorithms.