# A Novel Regularization Approach to Fair ML

arXiv: https://arxiv.org/abs/2208.06557 · HTML: https://mlsanity.com/paper/2208.06557/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 13 Aug 2022.

## Builds on (most cited first, 8 of 8)

- [ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R](https://mlsanity.com/paper/1508.04409/) (2015)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [On the Optimal Weighted ℓ2 Regularization in Overparameterized Linear Regression](https://mlsanity.com/paper/2006.05800/) (2020)
- [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021)
- [A simple measure of conditional dependence](https://mlsanity.com/paper/1910.12327/) (2019)
- [A survey of bias in Machine Learning through the prism of Statistical Parity for the Adult Data Set](https://mlsanity.com/paper/2003.14263/) (2020)
- [Achieving Fairness with a Simple Ridge Penalty](https://mlsanity.com/paper/2105.13817/) (2021)

## Built on by (most cited first, 3 of 3)

- [Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness](https://mlsanity.com/paper/2510.22363/) (2025)
- [dsld: A Socially Relevant Tool for Teaching Statistics](https://mlsanity.com/paper/2411.04228/) (2024)
- [TowerDebias: A Novel Unfairness Removal Method Based on the Tower Property](https://mlsanity.com/paper/2411.08297/) (2024)

## Abstract (arXiv)

A number of methods have been introduced for the fair ML issue, most of them complex and many of them very specific to the underlying ML moethodology. Here we introduce a new approach that is simple, easily explained, and potentially applicable to a number of standard ML algorithms. Explicitly Deweighted Features (EDF) reduces the impact of each feature among the proxies of sensitive variables, allowing a different amount of deweighting applied to each such feature. The user specifies the deweighting hyperparameters, to achieve a given point in the Utility/Fairness tradeoff spectrum. We also introduce a new, simple criterion for evaluating the degree of protection afforded by any fair ML method.