# The Benefits and Risks of Transductive Approaches for AI Fairness

arXiv: https://arxiv.org/abs/2406.12011 · HTML: https://mlsanity.com/paper/2406.12011/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 17 Jun 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [Fair Generative Modeling via Weak Supervision](https://mlsanity.com/paper/1910.12008/) (2019)
- [Class Rectification Hard Mining for Imbalanced Deep Learning](https://mlsanity.com/paper/1712.03162/) (2017)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Improving the Fairness of Deep Generative Models without Retraining](https://mlsanity.com/paper/2012.04842/) (2020)
- [Achieving Equalized Odds by Resampling Sensitive Attributes](https://mlsanity.com/paper/2006.04292/) (2020)
- [Fairness for Image Generation with Uncertain Sensitive Attributes](https://mlsanity.com/paper/2106.12182/) (2021)
- [Learning Soft Labels via Meta Learning](https://mlsanity.com/paper/2009.09496/) (2020)
- [On the Fairness of Generative Adversarial Networks (GANs)](https://mlsanity.com/paper/2103.00950/) (2021)
- [FORML: Learning to Reweight Data for Fairness](https://mlsanity.com/paper/2202.01719/) (2022)
- [Metric-Optimized Example Weights](https://mlsanity.com/paper/1805.10582/) (2018)
- [Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)](https://mlsanity.com/paper/2107.02565/) (2021)

## Abstract (arXiv)

Recently, transductive learning methods, which leverage holdout sets during training, have gained popularity for their potential to improve speed, accuracy, and fairness in machine learning models. Despite this, the composition of the holdout set itself, particularly the balance of sensitive sub-groups, has been largely overlooked. Our experiments on CIFAR and CelebA datasets show that compositional changes in the holdout set can substantially influence fairness metrics. Imbalanced holdout sets exacerbate existing disparities, while balanced holdouts can mitigate issues introduced by imbalanced training data. These findings underline the necessity of constructing holdout sets that are both diverse and representative.