Fair Ranking Metrics

Raj, Amifa

doi:10.1145/3523227.3547430

Cited by 2 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More and more works have attempted to propose fairness metrics, according to various constraints such as distance and ratio between the proportion of a protected attribute and the overall attribute proportion (K. Yang & Stoyanovich, 2017), pairwise comparisons regarding utility and prediction errors (Beutel et al, 2019; Kuhlman et al, 2019; Yao & Huang, 2017b), exposure distributions against the desired distribution (Geyik et al, 2019; K. Yang & Stoyanovich, 2017). Several studies have compared existing fairness metrics (Chouldechova, 2017; Garg et al, 2020; Hinnefeld et al, 2018; Raj et al, 2020; Sapiezynski et al, 2019). Unlike metrics that only capture fairness, our work focuses on incorporating fairness into a unified metric that also accounts for standard IR metrics.…”

Section: Related Workmentioning

confidence: 99%

FAIR: Fairness‐aware information retrieval evaluation

Gao

Shah

2022

Asso for Info Science & Tech

View full text Add to dashboard Cite

With the emerging needs of creating fairness-aware solutions for search and recommendation systems, a daunting challenge exists of evaluating such solutions. While many of the traditional information retrieval (IR) metrics can capture the relevance, diversity, and novelty for the utility with respect to users, they are not suitable for inferring whether the presented results are fair from the perspective of responsible information exposure. On the other hand, existing fairness metrics do not account for user utility or do not measure it adequately. To address this problem, we propose a new metric called FAIR. By unifying standard IR metrics and

show abstract