A Multivocal Literature Review on Privacy and Fairness in Federated Learning

TL;DR

This paper reviews current methods for integrating privacy and fairness in federated learning, highlighting the neglected relationship between these aspects and the need for comprehensive frameworks for real-world applications.

Contribution

It provides a multivocal literature review revealing the gap in understanding the privacy-fairness relationship in federated learning and advocates for integrated solutions.

Findings

Privacy and fairness are often treated separately in federated learning.

There is an inherent tension between privacy preservation and fairness objectives.

Current research lacks comprehensive frameworks addressing both privacy and fairness simultaneously.

Abstract

Federated Learning presents a way to revolutionize AI applications by eliminating the necessity for data sharing. Yet, research has shown that information can still be extracted during training, making additional privacy-preserving measures such as differential privacy imperative. To implement real-world federated learning applications, fairness, ranging from a fair distribution of performance to non-discriminative behaviour, must be considered. Particularly in high-risk applications (e.g. healthcare), avoiding the repetition of past discriminatory errors is paramount. As recent research has demonstrated an inherent tension between privacy and fairness, we conduct a multivocal literature review to examine the current methods to integrate privacy and fairness in federated learning. Our analyses illustrate that the relationship between privacy and fairness has been neglected, posing a critical risk for real-world applications. We highlight the need to explore the relationship between privacy, fairness, and performance, advocating for the creation of integrated federated learning frameworks.