Fairness in representation: quantifying stereotyping as a representational harm
Fairness in representation: quantifying stereotyping as a representational harm
Mohsen Abbasi,Sorelle A. Friedler,C. Scheidegger,Suresh Venkatasubramanian
TLDR
This paper formalizes two notions of stereotyping and shows how they manifest in later allocative harms within the machine learning pipeline and proposes mitigation strategies and demonstrates their effectiveness on synthetic datasets.
Abstract
While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention. In this paper, we formalize two notions of stereotyping and show how they manifest in later allocative harms within the machine learning pipeline. We also propose mitigation strategies and demonstrate their effectiveness on synthetic datasets.