Fairness-Aware Unsupervised Feature Selection
This addresses fairness issues in unsupervised feature selection for machine learning applications, offering a model-agnostic debiasing strategy that is incremental as it builds on existing feature selection methods.
The paper tackles the problem of unfairness in unsupervised feature selection, where existing methods risk amplifying discrimination by selecting features correlated with protected attributes like gender or race. It proposes a fairness-aware framework using kernel alignment to select features that preserve information while minimizing correlation with protected attributes, achieving a trade-off between utility and fairness on real-world datasets.
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.