at Google ScholarTitle data
Balbierer, Beatrice ; Heinlein, Lukas ; Zipperling, Domenique ; Kühl, Niklas:
A Multivocal Literature Review on Privacy and Fairness in Federated Learning.
In:
Proceedings of the 19th International Conference on Wirtschaftsinformatik (WI). -
Würzburg, Germany
,
2024
DOI: https://doi.org/10.48550/arXiv.2408.08666
Abstract in another language
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 achieved benefits to non-discriminative behavior, 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 comprehensive multivocal literature review to examine the current concepts 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, also fairness, and performance, advocating for the creation of comprehensive, holistic federated learning frameworks.