Interventional Fairness with Indirect Knowledge of Unobserved Protected Attributes

The deployment of machine learning (ML) systems in applications with societal impact has motivated the study of fairness for marginalized groups. Often, the protected attribute is absent from the training dataset for legal reasons. However, datasets still contain proxy attributes that capture protec...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Sainyam Galhotra, Karthikeyan Shanmugam, Prasanna Sattigeri, Kush R. Varshney
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2021-11-01
Serier:	Entropy
Fag:	causal fairness responsible data science
Online adgang:	https://www.mdpi.com/1099-4300/23/12/1571
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!