PraFFL: A Preference-Aware Scheme in Fair Federated Learning
This addresses fairness issues in federated learning for clients with diverse needs, though it is incremental as it builds on prior work by handling multiple preferences instead of single ones.
The paper tackles the trade-off between model performance and fairness in federated learning by proposing PraFFL, a scheme that generates preference-specific models in real time to adapt to clients' multiple preferences, showing linear convergence and outperforming six existing algorithms in adapting to different preferences.
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.