PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning

TL;DR

PUFFLE is a novel approach in federated learning that balances privacy, utility, and fairness, effectively reducing unfairness significantly with minimal utility loss while ensuring privacy.

Contribution

This paper introduces PUFFLE, the first method to simultaneously address privacy, utility, and fairness in federated learning.

Findings

Reduces model unfairness by up to 75%.

Maintains strict privacy guarantees during training.

Limits utility loss to 17% in worst cases.

Abstract

Training and deploying Machine Learning models that simultaneously adhere to principles of fairness and privacy while ensuring good utility poses a significant challenge. The interplay between these three factors of trustworthiness is frequently underestimated and remains insufficiently explored. Consequently, many efforts focus on ensuring only two of these factors, neglecting one in the process. The decentralization of the datasets and the variations in distributions among the clients exacerbate the complexity of achieving this ethical trade-off in the context of Federated Learning (FL). For the first time in FL literature, we address these three factors of trustworthiness. We introduce PUFFLE, a high-level parameterised approach that can help in the exploration of the balance between utility, privacy, and fairness in FL scenarios. We prove that PUFFLE can be effective across diverse datasets, models, and data distributions, reducing the model unfairness up to 75%, with a maximum reduction in the utility of 17% in the worst-case scenario, while maintaining strict privacy guarantees during the FL training.