A Fairness-Aware Semi-Supervised Clustering Method

Abstract

We present a semi-supervised clustering algorithm that incorporates a fairness component, implemented as a variant of K-Means but extendable to other center-based approaches. Fairness is defined as producing balanced clusters and is measured using a normalized entropy metric. Experiments on real-world and LLM-generated datasets show consistent improvements in fairness and accuracy over baseline K-Means, along with an analysis of the effect of the fairness component strength.