# Fair Generative Modeling via Weak Supervision

arXiv: https://arxiv.org/abs/1910.12008 · HTML: https://mlsanity.com/paper/1910.12008/

## Key facts

- Cited by 114 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2019.

## Built on by (most cited first, 30 of 114)

- [Pretrained Transformers as Universal Computation Engines](https://mlsanity.com/paper/2103.05247/) (2021)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks](https://mlsanity.com/paper/2110.12884/) (2021)
- [Understanding and Evaluating Racial Biases in Image Captioning](https://mlsanity.com/paper/2106.08503/) (2021)
- [How to Backdoor Diffusion Models?](https://mlsanity.com/paper/2212.05400/) (2022)
- [D2C: Diffusion-Denoising Models for Few-shot Conditional Generation](https://mlsanity.com/paper/2106.06819/) (2021)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)
- [VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models](https://mlsanity.com/paper/2306.06874/) (2023)
- [A Systematic Study of Bias Amplification](https://mlsanity.com/paper/2201.11706/) (2022)
- [ITI-GEN: Inclusive Text-to-Image Generation](https://mlsanity.com/paper/2309.05569/) (2023)
- [Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias](https://mlsanity.com/paper/2403.07857/) (2024)
- [Directional Bias Amplification](https://mlsanity.com/paper/2102.12594/) (2021)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers](https://mlsanity.com/paper/2203.04913/) (2022)
- [Balancing Act: Distribution-Guided Debiasing in Diffusion Models](https://mlsanity.com/paper/2402.18206/) (2024)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Discover the Unknown Biased Attribute of an Image Classifier](https://mlsanity.com/paper/2104.14556/) (2021)
- [Don't Play Favorites: Minority Guidance for Diffusion Models](https://mlsanity.com/paper/2301.12334/) (2023)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)
- [Featurized Density Ratio Estimation](https://mlsanity.com/paper/2107.02212/) (2021)
- [Fairness Reprogramming](https://mlsanity.com/paper/2209.10222/) (2022)
- [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)
- [Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models](https://mlsanity.com/paper/2207.01056/) (2022)
- [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)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Training Unbiased Diffusion Models From Biased Dataset](https://mlsanity.com/paper/2403.01189/) (2024)

## Abstract (arXiv)

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine learning. We present a weakly supervised algorithm for overcoming dataset bias for deep generative models. Our approach requires access to an additional small, unlabeled reference dataset as the supervision signal, thus sidestepping the need for explicit labels on the underlying bias factors. Using this supplementary dataset, we detect the bias in existing datasets via a density ratio technique and learn generative models which efficiently achieve the twin goals of: 1) data efficiency by using training examples from both biased and reference datasets for learning; and 2) data generation close in distribution to the reference dataset at test time. Empirically, we demonstrate the efficacy of our approach which reduces bias w.r.t. latent factors by an average of up to 34.6% over baselines for comparable image generation using generative adversarial networks.