# Exploring Rawlsian Fairness for K-Means Clustering

arXiv: https://arxiv.org/abs/2205.02052 · HTML: https://mlsanity.com/paper/2205.02052/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 4 May 2022.

## Builds on (most cited first, 10 of 10)

- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Fair Clustering Through Fairlets](https://mlsanity.com/paper/1802.05733/) (2018)
- [Proportionally Fair Clustering](https://mlsanity.com/paper/1905.03674/) (2019)
- [Fair k-Center Clustering for Data Summarization](https://mlsanity.com/paper/1901.08628/) (2019)
- [Individual Fairness for k-Clustering](https://mlsanity.com/paper/2002.06742/) (2020)
- [A Center in Your Neighborhood: Fairness in Facility Location](https://mlsanity.com/paper/1908.09041/) (2019)
- [Fairness in Clustering with Multiple Sensitive Attributes](https://mlsanity.com/paper/1910.05113/) (2019)
- [A Notion of Individual Fairness for Clustering](https://mlsanity.com/paper/2006.04960/) (2020)
- [Representativity Fairness in Clustering](https://mlsanity.com/paper/2010.07054/) (2020)
- [Rawlsian Fair Adaptation of Deep Learning Classifiers](https://mlsanity.com/paper/2105.14890/) (2021)

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

- [Holistic Survey of Privacy and Fairness in Machine Learning](https://mlsanity.com/paper/2307.15838/) (2023)

## Abstract (arXiv)

We conduct an exploratory study that looks at incorporating John Rawls' ideas on fairness into existing unsupervised machine learning algorithms. Our focus is on the task of clustering, specifically the k-means clustering algorithm. To the best of our knowledge, this is the first work that uses Rawlsian ideas in clustering. Towards this, we attempt to develop a postprocessing technique i.e., one that operates on the cluster assignment generated by the standard k-means clustering algorithm. Our technique perturbs this assignment over a number of iterations to make it fairer according to Rawls' difference principle while minimally affecting the overall utility. As the first step, we consider two simple perturbation operators -- R1 and R2 -- that reassign examples in a given cluster assignment to new clusters; R1 assigning a single example to a new cluster, and R2 a pair of examples to new clusters. Our experiments on a sample of the Adult dataset demonstrate that both operators make meaningful perturbations in the cluster assignment towards incorporating Rawls' difference principle, with R2 being more efficient than R1 in terms of the number of iterations. However, we observe that there is still a need to design operators that make significantly better perturbations. Nevertheless, both operators provide good baselines for designing and comparing any future operator, and we hope our findings would aid future work in this direction.