# Learning Fair and Transferable Representations

arXiv: https://arxiv.org/abs/1906.10673 · HTML: https://mlsanity.com/paper/1906.10673/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2019.

## Built on by (most cited first, 6 of 6)

- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [Fairness and Accuracy under Domain Generalization](https://mlsanity.com/paper/2301.13323/) (2023)
- [Impossibility results for fair representations](https://mlsanity.com/paper/2107.03483/) (2021)
- [Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML](https://mlsanity.com/paper/2306.09297/) (2023)
- [A Survey on Preserving Fairness Guarantees in Changing Environments](https://mlsanity.com/paper/2211.07530/) (2022)
- [EiFFFeL: Enforcing Fairness in Forests by Flipping Leaves](https://mlsanity.com/paper/2112.14435/) (2021)

## Abstract (arXiv)

Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness. One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints. In this work we measure fairness according to demographic parity. This requires the probability of the possible model decisions to be independent of the sensitive information. We argue that the goal of imposing demographic parity can be substantially facilitated within a multitask learning setting. We leverage task similarities by encouraging a shared fair representation across the tasks via low rank matrix factorization. We derive learning bounds establishing that the learned representation transfers well to novel tasks both in terms of prediction performance and fairness metrics. We present experiments on three real world datasets, showing that the proposed method outperforms state-of-the-art approaches by a significant margin.