Fairness in Clustering with Multiple Sensitive Attributes

Abstract

A clustering may be considered as fair on pre-specified sensitive attributes if the proportions of sensitive attribute groups in each cluster reflect that in the dataset. In this paper, we consider the task of fair clustering for scenarios involving multiple multi-valued or numeric sensitive attributes. We propose a fair clustering method, \textit{FairKM} (Fair K-Means), that is inspired by the popular K-Means clustering formulation. We outline a computational notion of fairness which is used along with a cluster coherence objective, to yield the FairKM clustering method. We empirically evaluate our approach, wherein we quantify both the quality and fairness of clusters, over real-world datasets. Our experimental evaluation illustrates that the clusters generated by FairKM fare significantly better on both clustering quality and fair representation of sensitive attribute groups compared to the clusters from a state-of-the-art baseline fair clustering method.

Proceedings of the 23rd International Conference on Extending Database Technology (EDBT 2020), 30th March-2nd April, 2020

References in corpus (6)

• Distributed Representations of Sentences and Documents
• Clustering without Over-Representation
• Fair k-Center Clustering for Data Summarization
• Fair Coresets and Streaming Algorithms for Fair k-Means Clustering
• Towards Fair Deep Clustering With Multi-State Protected Variables
• Principal Fairness: Removing Bias via Projections

Cited by in corpus (9)

• A survey on datasets for fairness-aware machine learning
• Individual Fairness for $k$-Clustering
• A review of clustering models in educational data science towards fairness-aware learning
• Representativity Fairness in Clustering
• Approximation Algorithms for Socially Fair Clustering
• A Stochastic Alternating Balance $k$-Means Algorithm for Fair Clustering
• Whither Fair Clustering?
• Fair Outlier Detection
• Fairness Degrading Adversarial Attacks Against Clustering Algorithms