Hidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability
Abstract
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 utility of a user is the exposure given to the items they interact with, relative to that of an ideal ranking. We consider utility parity across user groups, as well as its category-aware refinement, conditional utility parity, which requires parity within each category of items. Following a recent view of fairness as distributional stability, we show that both criteria are equivalent to the stability of the utility under changes in the composition of user groups. Optimizing over mixtures of ranking policies leads to a second-order cone program, for which we provide generalization bounds. A numerical study validates our theoretical findings.
Related
- Multi-Sensitive Distributional Fairness: Joint Wasserstein Audits and Shapley Allocation
- New Bounds on Distributional Sectional Category and Applications to Distributional Homotopic Distance
- A Novel Intuitionistic Fuzzy Entropy with Comprehensive Ranking-Stability Analysis: An Entropy-Weighted IF-TOPSIS Framework
- The Role of Uncertainty in Assessing the Fairness of Machine Learning Models
- Equality, Equity, and Causality in Fairness Research: A Commentary on Cheng (2026)
BibTeX
@misc{taturyan2026hidden,
title = {{Hidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability}},
author = {Gayane Taturyan and Charlotte Laclau and Stephan Clémençon},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40182},
eprint = {2610.40182},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40182},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Hidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability
AU - Gayane Taturyan
AU - Charlotte Laclau
AU - Stephan Clémençon
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.40182
UR - https://arxiv.org/abs/2610.40182
AB - 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 utility of a user is the exposure given to the items they interact with, relative to that of an ideal ranking. We consider utility parity across user groups, as well as its category-aware refinement, conditional utility parity, which requires parity within each category of items. Following a recent view of fairness as distributional stability, we show that both criteria are equivalent to the stability of the utility under changes in the composition of user groups. Optimizing over mixtures of ranking policies leads to a second-order cone program, for which we provide generalization bounds. A numerical study validates our theoretical findings.
ER -