# AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data

arXiv: https://arxiv.org/abs/2503.05665 · HTML: https://mlsanity.com/paper/2503.05665/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 52 of its 64 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)
- Synthetic data and self-improvement for LLMs / [LLM synthetic data generation](https://mlsanity.com/synth/llm-synthetic-data-generation/)

## Builds on (most cited first, 30 of 52)

- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (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)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Large-Scale Methods for Distributionally Robust Optimization](https://mlsanity.com/paper/2010.05893/) (2020)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Fair Generative Modeling via Weak Supervision](https://mlsanity.com/paper/1910.12008/) (2019)
- [The Measure and Mismeasure of Fairness](https://mlsanity.com/paper/1808.00023/) (2018)

## Built on by (most cited first, 5 of 5)

- [How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions](https://mlsanity.com/paper/2511.07091/) (2025)
- [Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement](https://mlsanity.com/paper/2606.24161/) (2026)
- [Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects](https://mlsanity.com/paper/2605.27407/) (2026)
- [Position: Fairness Failure in Generative Models is an Evaluation Problem](https://mlsanity.com/paper/2608.16974/) (2026)
- [DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching](https://mlsanity.com/paper/2609.16149/) (2026)

## Abstract (arXiv)

Recent advances in generative models have sparked research on improving model fairness with AI-generated data. However, existing methods often face limitations in the diversity and quality of synthetic data, leading to compromised fairness and overall model accuracy. Moreover, many approaches rely on the availability of demographic group labels, which are often costly to annotate. This paper proposes AIM-Fair, aiming to overcome these limitations and harness the potential of cutting-edge generative models in promoting algorithmic fairness. We investigate a fine-tuning paradigm starting from a biased model initially trained on real-world data without demographic annotations. This model is then fine-tuned using unbiased synthetic data generated by a state-of-the-art diffusion model to improve its fairness. Two key challenges are identified in this fine-tuning paradigm, 1) the low quality of synthetic data, which can still happen even with advanced generative models, and 2) the domain and bias gap between real and synthetic data. To address the limitation of synthetic data quality, we propose Contextual Synthetic Data Generation (CSDG) to generate data using a text-to-image diffusion model (T2I) with prompts generated by a context-aware LLM, ensuring both data diversity and control of bias in synthetic data. To resolve domain and bias shifts, we introduce a novel selective fine-tuning scheme in which only model parameters more sensitive to bias and less sensitive to domain shift are updated. Experiments on CelebA and UTKFace datasets show that our AIM-Fair improves model fairness while maintaining utility, outperforming both fully and partially fine-tuned approaches to model fairness.