Towards Group Fairness with Multiple Sensitive Attributes in Federated Foundation Models

TL;DR

This paper introduces a causal analysis framework for achieving and understanding group fairness across multiple sensitive attributes in federated foundation models, addressing limitations of prior single-attribute fairness methods.

Contribution

It extends federated foundation models to handle multiple sensitive attributes simultaneously and provides causal insights into their interdependencies for fairness.

Findings

Effective causal analysis of multiple sensitive attributes.

Improved interpretability of fairness dependencies.

Validated approach through extensive experiments.

Abstract

The deep integration of foundation models (FM) with federated learning (FL) enhances personalization and scalability for diverse downstream tasks, making it crucial in sensitive domains like healthcare. Achieving group fairness has become an increasingly prominent issue in the era of federated foundation models (FFMs), since biases in sensitive attributes might lead to inequitable treatment for under-represented demographic groups. Existing studies mostly focus on achieving fairness with respect to a single sensitive attribute. This renders them unable to provide clear interpretability of dependencies among multiple sensitive attributes which is required to achieve group fairness. Our paper takes the first attempt towards a causal analysis of the relationship between group fairness across various sensitive attributes in the FFM. We extend the FFM structure to trade off multiple sensitive attributes simultaneously and quantify the causal effect behind the group fairness through causal discovery and inference. Extensive experiments validate its effectiveness, offering insights into interpretability towards building trustworthy and fair FFM systems.