4 papers
Hidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability
Gayane Taturyan, Charlotte Laclau, Stephan Clémençon
We study the problem of fair ranking in recommender systems. We provide a formal probabilistic framework in which ranking policies are distributions over permutations, and the util…
A Comprehensive View of Fairness through Distributional Stability
Gayane Taturyan, Charlotte Laclau, Stephan Clémencon
We view fairness as a property of distributional stability. Rather than assessing a predictor under a fixed data distribution, we study how its predictions change under perturbatio…
Randomized multi-class classification under system constraints: a unified approach via post-processing
Evgenii Chzhen, Mohamed Hebiri, Gayane Taturyan
We study the problem of multi-class classification under system-level constraints expressible as linear functionals over randomized classifiers. We propose a post-processing approa…
Regression under demographic parity constraints via unlabeled post-processing
Evgenii Chzhen, Mohamed Hebiri, Gayane Taturyan
We address the problem of performing regression while ensuring demographic parity, even without access to sensitive attributes during inference. We present a general-purpose post-p…