Addressing multiple metrics of group fairness in data-driven decision making
By Marius Miron, Songül Tolan, Emilia G'omez, Carlos Castillo. 2020
9 citations recorded by the source corpus.
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.
Subfields: Management Information Systems, Safety Research, Sociology and Political Science
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Management Information Systems
In Safety Research
In Sociology and Political Science
Citations in the corpus
- Mathematical optimization in classification and regression trees (2021, methodology): “Indeed, given a norm ⋅ and a set A ⊂ ℝ p of allowed movements from x 0 , one can solve a nonlinear problem of the form: The use of Machine Learning models in socially sensitive decision-making calls for analyzing their fairness (Iosifidis and Ntoutsi 2019; Miron et al. 2020; Zafar et al. 2017).”