Quantifying Query Fairness Under Unawareness

TL;DR

This paper introduces a robust quantification-based fairness estimator for ranking algorithms that effectively measures fairness across multiple sensitive attributes without requiring true group labels, addressing dataset shift issues.

Contribution

It proposes the first reliable protocol for measuring fairness under unawareness across multiple queries and groups using a quantification approach.

Findings

Outperforms existing baselines in fairness estimation.

Handles multiple sensitive attributes beyond binary classifications.

Establishes a reliable protocol for fairness measurement under unawareness.

Abstract

Traditional ranking algorithms are designed to retrieve the most relevant items for a user's query, but they often inherit biases from data that can unfairly disadvantage vulnerable groups. Fairness in information access systems (IAS) is typically assessed by comparing the distribution of groups in a ranking to a target distribution, such as the overall group distribution in the dataset. These fairness metrics depend on knowing the true group labels for each item. However, when groups are defined by demographic or sensitive attributes, these labels are often unknown, leading to a setting known as "fairness under unawareness". To address this, group membership can be inferred using machine-learned classifiers, and group prevalence is estimated by counting the predicted labels. Unfortunately, such an estimation is known to be unreliable under dataset shift, compromising the accuracy of fairness evaluations. In this paper, we introduce a robust fairness estimator based on quantification that effectively handles multiple sensitive attributes beyond binary classifications. Our method outperforms existing baselines across various sensitive attributes and, to the best of our knowledge, is the first to establish a reliable protocol for measuring fairness under unawareness across multiple queries and groups.