# Fairness-Aware Unsupervised Feature Selection

arXiv: https://arxiv.org/abs/2106.02216 · HTML: https://mlsanity.com/paper/2106.02216/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Fair Clustering Through Fairlets](https://mlsanity.com/paper/1802.05733/) (2018)
- [The Frontiers of Fairness in Machine Learning](https://mlsanity.com/paper/1810.08810/) (2018)
- [Fairness in Deep Learning: A Computational Perspective](https://mlsanity.com/paper/1908.08843/) (2019)
- [Invariant Representations without Adversarial Training](https://mlsanity.com/paper/1805.09458/) (2018)
- [Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination](https://mlsanity.com/paper/1906.00285/) (2019)
- [Scalable Fair Clustering](https://mlsanity.com/paper/1902.03519/) (2019)
- [Guarantees for Spectral Clustering with Fairness Constraints](https://mlsanity.com/paper/1901.08668/) (2019)
- [A causal framework for discovering and removing direct and indirect discrimination](https://mlsanity.com/paper/1611.07509/) (2016)
- [Feature Selection: A Data Perspective](https://mlsanity.com/paper/1601.07996/) (2016)
- [Fair Coresets and Streaming Algorithms for Fair k-Means Clustering](https://mlsanity.com/paper/1812.10854/) (2018)

## Built on by (most cited first, 10 of 10)

- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift](https://mlsanity.com/paper/2505.23027/) (2025)
- [Outlier Detection Bias Busted: Understanding Sources of Algorithmic Bias through Data-centric Factors](https://mlsanity.com/paper/2408.13667/) (2024)
- [Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation](https://mlsanity.com/paper/2309.14243/) (2023)
- [On the Cause of Unfairness: A Training Sample Perspective](https://mlsanity.com/paper/2306.17828/) (2023)
- [Kernel Alignment for Unsupervised Feature Selection via Matrix Factorization](https://mlsanity.com/paper/2403.14688/) (2024)
- [Evaluating Fair Feature Selection in Machine Learning for Healthcare](https://mlsanity.com/paper/2403.19165/) (2024)
- [Beyond Correlation: Causal Multi-View Unsupervised Feature Selection Learning](https://mlsanity.com/paper/2509.13763/) (2025)
- [Evolved Sample Weights for Bias Mitigation: Effectiveness Depends on the Fairness Objective](https://mlsanity.com/paper/2511.20909/) (2025)

## Abstract (arXiv)

Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing unsupervised feature selection algorithms do not have fairness considerations and suffer from a high risk of amplifying discrimination by selecting features that are over associated with protected attributes such as gender, race, and ethnicity. In this paper, we make an initial investigation of the fairness-aware unsupervised feature selection problem and develop a principled framework, which leverages kernel alignment to find a subset of high-quality features that can best preserve the information in the original feature space while being minimally correlated with protected attributes. Specifically, different from the mainstream in-processing debiasing methods, our proposed framework can be regarded as a model-agnostic debiasing strategy that eliminates biases and discrimination before downstream learning algorithms are involved. Experimental results on multiple real-world datasets demonstrate that our framework achieves a good trade-off between utility maximization and fairness promotion.