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

TL;DR

This paper introduces a new concept of Income Fairness in ranking systems, accounting for factors like time that influence provider income, and proposes an algorithm that optimizes both relevance and income fairness.

Contribution

It formalizes Income Fairness, develops a measurement metric, and proposes the DIDRF algorithm that outperforms existing methods in optimizing fairness considering time-income factors.

Findings

Existing exposure fairness algorithms fail to optimize income fairness.

DIDRF effectively balances relevance and income fairness in diverse settings.

DIDRF outperforms state-of-the-art methods in both offline and online experiments.

Abstract

Ranking is central to information distribution in web search and recommendation. Nowadays, in ranking optimization, the fairness to item providers is viewed as a crucial factor alongside ranking relevance for users. There are currently numerous concepts of fairness and one widely recognized fairness concept is Exposure Fairness. However, it relies primarily on exposure determined solely by position, overlooking other factors that significantly influence income, such as time. To address this limitation, we propose to study ranking fairness when the provider utility is influenced by other contextual factors and is neither equal to nor proportional to item exposure. We give a formal definition of Income Fairness and develop a corresponding measurement metric. Simulated experiments show that existing-exposure-fairness-based ranking algorithms fail to optimize the proposed income fairness. Therefore, we propose the Dynamic-Income-Derivative-aware Ranking Fairness algorithm, which, based on the marginal income gain at the present timestep, uses Taylor-expansion-based gradients to simultaneously optimize effectiveness and income fairness. In both offline and online settings with diverse time-income functions, DIDRF consistently outperforms state-of-the-art methods.