PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning
This addresses the problem of achieving ethical trade-offs in federated learning for practitioners, though it is incremental as it combines existing factors in a new way.
The paper tackles the challenge of balancing privacy, utility, and fairness in federated learning, introducing PUFFLE, which reduces model unfairness by up to 75% with a maximum utility reduction of 17% while maintaining strict privacy.
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.