PraFFL: A Preference-Aware Scheme in Fair Federated Learning

TL;DR

PraFFL introduces a novel preference-aware federated learning scheme that adaptively generates models tailored to individual client preferences, balancing fairness and performance in practical, multi-preference scenarios.

Contribution

This paper presents PraFFL, a real-time, preference-adaptive federated learning scheme that handles multiple client preferences, with theoretical guarantees and superior experimental performance.

Findings

PraFFL achieves linear convergence.

PraFFL outperforms six existing fair federated learning algorithms.

PraFFL effectively adapts to diverse client preferences.

Abstract

Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model among groups (e.g., male or female) of diverse sensitive features. However, there is a trade-off between model performance and fairness, i.e., improving model fairness will decrease model performance. Existing approaches have characterized such a trade-off by introducing hyperparameters to quantify client's preferences for model fairness and model performance. Nevertheless, these approaches are limited to scenarios where each client has only a single pre-defined preference, and fail to work in practical systems where each client generally has multiple preferences. To this end, we propose a Preference-aware scheme in Fair Federated Learning (called PraFFL) to generate preference-specific models in real time. PraFFL can adaptively adjust the model based on each client's preferences to meet their needs. We theoretically prove that PraFFL can offer the optimal model tailored to an arbitrary preference of each client, and show its linear convergence. Experimental results show that our proposed PraFFL outperforms six fair federated learning algorithms in terms of the model's capability of adapting to clients' different preferences. Our implementation is available at https://github.com/rG223/PraFFL.