# Debiasing representations by removing unwanted variation due to protected attributes

arXiv: https://arxiv.org/abs/1807.00461 · HTML: https://mlsanity.com/paper/1807.00461/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 1 of 1)

- [Individually Fair Gradient Boosting](https://mlsanity.com/paper/2103.16785/) (2021)

## Abstract (arXiv)

We propose a regression-based approach to removing implicit biases in representations. On tasks where the protected attribute is observed, the method is statistically more efficient than known approaches. Further, we show that this approach leads to debiased representations that satisfy a first order approximation of conditional parity. Finally, we demonstrate the efficacy of the proposed approach by reducing racial bias in recidivism risk scores.