Measuring and mitigating voting access disparities: a study of race and polling locations in Florida and North Carolina

no code implementations • 30 May 2022 • Mohsen Abbasi, Suresh Venkatasubramanian, Sorelle A. Friedler, Kristian Lum, Calvin Barrett

In this paper, we quantify access to polling locations, developing a methodology for the calibrated measurement of racial disparities in polling location "load" and distance to polling locations.

Fair clustering via equitable group representations

no code implementations • 19 Jun 2020 • Mohsen Abbasi, Aditya Bhaskara, Suresh Venkatasubramanian

A core principle in most clustering problems is that a cluster center should be representative of the cluster it represents, by being "close" to the points associated with it.

Clustering Fairness

Fairness in representation: quantifying stereotyping as a representational harm

no code implementations • 28 Jan 2019 • Mohsen Abbasi, Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention.

BIG-bench Machine Learning Fairness