Beyond Exposure: Optimizing Ranking Fairness with Non-linear Time-Income Functions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Xuancheng, Yang, Tao, Zhou, Yujia, Ai, Qingyao, Liu, Yiqun
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914595841507328
author Li, Xuancheng
Yang, Tao
Zhou, Yujia
Ai, Qingyao
Liu, Yiqun
author_facet Li, Xuancheng
Yang, Tao
Zhou, Yujia
Ai, Qingyao
Liu, Yiqun
contents Ranking systems in web search and recommendation allocate attention among items and providers, and therefore need to balance relevance-based effectiveness with provider fairness. Existing fair-ranking methods commonly focus on exposure fairness, where cumulative exposure is allocated in proportion to item merit. However, exposure is often only an intermediate signal: the actual utility received by a provider may depend on context-dependent conversion from exposure to income, such as clicks, purchases, or advertising value. This paper studies fair ranking under context-dependent provider utility, which we refer to as income. We formalize income fairness by requiring cumulative provider income to be proportional to relevance, and define an income-unfairness metric based on this proportionality condition. We then propose DIDRF, a Dynamic-Income-Derivative-aware Ranking Fairness algorithm for income-fair ranking. DIDRF uses the quadratic structure of income-fairness violations to derive a state-aware scoring rule that jointly considers ranking effectiveness and the marginal effect of each ranking decision on cumulative income fairness. Experiments on standard learning-to-rank datasets with log-calibrated semi-synthetic income environments based on advertising and e-commerce logs show that DIDRF consistently improves income fairness over representative fair-ranking baselines while preserving competitive ranking effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03345
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Exposure: Optimizing Ranking Fairness with Non-linear Time-Income Functions
Li, Xuancheng
Yang, Tao
Zhou, Yujia
Ai, Qingyao
Liu, Yiqun
Information Retrieval
Ranking systems in web search and recommendation allocate attention among items and providers, and therefore need to balance relevance-based effectiveness with provider fairness. Existing fair-ranking methods commonly focus on exposure fairness, where cumulative exposure is allocated in proportion to item merit. However, exposure is often only an intermediate signal: the actual utility received by a provider may depend on context-dependent conversion from exposure to income, such as clicks, purchases, or advertising value. This paper studies fair ranking under context-dependent provider utility, which we refer to as income. We formalize income fairness by requiring cumulative provider income to be proportional to relevance, and define an income-unfairness metric based on this proportionality condition. We then propose DIDRF, a Dynamic-Income-Derivative-aware Ranking Fairness algorithm for income-fair ranking. DIDRF uses the quadratic structure of income-fairness violations to derive a state-aware scoring rule that jointly considers ranking effectiveness and the marginal effect of each ranking decision on cumulative income fairness. Experiments on standard learning-to-rank datasets with log-calibrated semi-synthetic income environments based on advertising and e-commerce logs show that DIDRF consistently improves income fairness over representative fair-ranking baselines while preserving competitive ranking effectiveness.
title Beyond Exposure: Optimizing Ranking Fairness with Non-linear Time-Income Functions
topic Information Retrieval
url https://arxiv.org/abs/2602.03345