A Multivocal Literature Review on Privacy and Fairness in Federated Learning
This work identifies a critical oversight in federated learning research that could impact high-risk domains such as healthcare, though it is incremental as it reviews existing literature rather than proposing new methods.
The paper conducts a literature review on privacy and fairness in federated learning, finding that their relationship is often neglected, which poses risks for real-world applications like healthcare, and advocates for integrated frameworks to address this gap.
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.