FACROC: a fairness measure for FAir Clustering through ROC curves
This work addresses the need for better fairness evaluation in clustering for researchers and practitioners, but it is incremental as it builds on existing fairness measures by adding a visual component.
The paper tackles the problem of evaluating fairness in clustering by introducing FACROC, a visual-based fairness measure that uses ROC curves and AUCC to assess clustering quality across protected attribute values, showing it is beneficial for visually evaluating fairness in clustering models.
Fair clustering has attracted remarkable attention from the research community. Many fairness measures for clustering have been proposed; however, they do not take into account the clustering quality w.r.t. the values of the protected attribute. In this paper, we introduce a new visual-based fairness measure for fair clustering through ROC curves, namely FACROC. This fairness measure employs AUCC as a measure of clustering quality and then computes the difference in the corresponding ROC curves for each value of the protected attribute. Experimental results on several popular datasets for fairness-aware machine learning and well-known (fair) clustering models show that FACROC is a beneficial method for visually evaluating the fairness of clustering models.