Towards Fair Decision Boundaries in Clustering: Integrating Disparate Impact Criteria into Maximum Margin Clustering

Extensive application of machine learning in the areas that impact human lives have significantly spurred considerable interest in developing algorithms that are demonstrably fair. Recent efforts in this field have led to the creation of numerous algorithms addressing the paradigm of clustering with fairness constraints. In this research, we adopt disparate impact criteria from supervised learning scenarios and incorporate it into clustering by specifically focusing on decision boundary fairness. The existing fairness definitions in clustering scenarios mostly deal with the Balance of the clusters or the representation of the sensitive groups in the clusters. We developed a new algorithm called Fair Maximum Margin Clustering (FMMC), by incorporating the disparate impact criteria into the Maximum Margin Clustering (MMC) algorithm. The FMMC algorithm ensures that the distance of each data point from the hyperplane is uncorrelated with that data point’s sensitive attribute value. This constraint is designed to prevent any sensitive group from being negatively impacted by the decision boundary. We show that the performance of the FMMC algorithm is better than that of MMC algorithm in terms of traditional fairness measures such as Balance. We also demonstrate that the FMMC algorithm achieves fair clustering while maintaining the clustering performance of the original MMC algorithm. We validate the effectiveness of our approach through experiments on synthetic and real-world datasets.