2020/03/10 by Marius Miron, Miron, Marius, Songül Tolan +5
Business, Management and Accounting · Social Sciences · #Big Data and Business Intelligence #Computers and Society (cs.CY) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Qualitative Comparative Analysis Research
paper · pdf · doi:10.48550/arxiv.2003.04794
openalex publication_date 2020/03/10 · openalex created_date 2020/03/23 · openalex updated_date 2026/07/28
The Fairness, Accountability, and Transparency in Machine Learning (FAT-ML) literature proposes a varied set of group fairness metrics to measure discrimination against socio-demographic groups that are characterized by a protected feature, such as gender or race.Such a system can be deemed as either fair or unfair depending on the choice of the metric. Several metrics have been proposed, some of them incompatible with each other.We do so empirically, by observing that several of these metrics cluster together in two or three main clusters for the same groups and machine learning methods. In addition, we propose a robust way to visualize multidimensional fairness in two dimensions through a Principal Component Analysis (PCA) of the group fairness metrics. Experimental results on multiple datasets show that the PCA decomposition explains the variance between the metrics with one to three components.