Recent methods leverage a hypernet to handle the performance-fairness trade-offs in federated learning. This hypernet maps the clients' preferences between model performance and fairness to preference-specifc models on the trade-off curve, known as local Pareto front. However, existing methods typically adopt a uniform preference sampling distribution to train the hypernet across clients, neglecting the inherent heterogeneity of their local Pareto fronts. Meanwhile, from the perspective of generalization, they do not consider the gap between local and global Pareto fronts on the global dataset. To address these limitations, we propose HetPFL to effectively learn both local and global Pareto fronts. HetPFL comprises Preference Sampling Adaptation (PSA) and Preference-aware Hypernet Fusion (PHF). PSA adaptively determines the optimal preference sampling distribution for each client to accommodate heterogeneous local Pareto fronts. While PHF performs preference-aware fusion of clients' hypernets to ensure the performance of the global Pareto front. We prove that HetPFL converges linearly with respect to the number of rounds, under weaker assumptions than existing methods. Extensive experiments on four datasets show that HetPFL significantly outperforms seven baselines in terms of the quality of learned local and global Pareto fronts.

Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model for any special group (e.g., male or female) of sensitive features. However, there is a trade-off between model performance and fairness, i.e., improving fairness will decrease model performance. Existing approaches have characterized such a trade-off by introducing hyperparameters to quantify client's preferences for fairness and model performance. Nevertheless, these methods are limited to scenarios where each client has only a single pre-defined preference. In practical systems, each client may simultaneously have multiple preferences for the model performance and fairness. The key challenge is to design a method that allows the model to adapt to diverse preferences of each client in real time. To this end, we propose a Preference-aware scheme in Fair Federated Learning paradigm (called PraFFL). PraFFL can adaptively adjust the model based on each client's preferences to meet their needs. We theoretically prove that PraFFL can provide the optimal model for client's arbitrary preferences. Experimental results show that our proposed PraFFL outperforms five existing fair federated learning algorithms in terms of the model's capability in adapting to clients' different preferences.