Robust Personalized Federated Learning under Demographic Fairness Heterogeneity
Robust Personalized Federated Learning under Demographic Fairness Heterogeneity
复制标题
DOI：
10.1109/bigdata55660.2022.10020554
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Alycia N. Carey;Wei Du;Xintao Wu
中科院分区：
文献类型：
--
作者：
Alycia N. Carey;Wei Du;Xintao Wu
个性化联邦学习（PFL）使联邦中的每个客户端都能够获得针对其特定数据分布或任务定制的模型，而不会丧失以联邦方式进行培训的好处。然而，人口群体公平的概念在PFL中尚未得到广泛研究。此外，公平性异质性-当不是所有客户端都执行相同的本地公平性度量时-根本没有被研究。为了填补这一空白，我们提出了公平超网络（FHN），这是一种基于超网络的个性化联邦学习架构，对统计（例如，非IID和不平衡数据）和公平性异质性。我们从理论上表明，授予客户端的能力，独立选择多个（可能相互冲突）的公平性约束，如人口统计学的奇偶性或均衡的赔率，并没有打破以前证明的泛化范围内使用的超网络在联邦设置。此外，我们在多个公平的联邦学习设置中根据几个基线对FHN进行了经验测试，我们发现在处理具有异构公平性指标的客户端时，FHN的性能优于所有其他联邦基线。我们进一步展示了FHN的可扩展性，以表明当联邦的规模增加时，对客户端的准确性和公平性的退化最小。此外，我们实证验证我们的理论分析，以显示FHN推广以及新客户。据我们所知，我们的FHN架构是第一个考虑对公平性异质性的容忍度的架构，这使得客户端可以自由地个性化本地训练期间实施的公平性度量。
Personalized federated learning (PFL) gives each client in a federation the power to obtain a model tailored to their specific data distribution or task without the client forfeiting the benefits of training in a federated manner. However, the concept of demographic group fairness has not been widely studied in PFL. Further, fairness heterogeneity – when not all clients enforce the same local fairness metric – has not been studied at all. To fill this gap, we propose Fair Hypernetworks (FHN), a personalized federated learning architecture based on hypernetworks that is robust to statistical (e.g., non-IID and unbalanced data) and fairness heterogeneity. We theoretically show that granting clients the ability to independently choose multiple (possibly conflicting) fairness constraints, such as demographic parity or equalized odds, does not break previously proven generalization bounds on hypernetworks used in the federated setting. Additionally, we empirically test FHN against several baselines in multiple fair federated learning settings, and we find t hat F HN outperforms all other federated baselines when handling clients with heterogeneous fairness metrics. We further demonstrate the scalability of FHN to show that minimal degradation to the accuracy and the fairness of the clients occurs when the federation grows in size. Additionally, we empirically validate our theoretical analysis to show FHN generalizes well to new clients. To our knowledge, our FHN architecture is the first to consider tolerance to fairness heterogeneity which gives clients the freedom to personalize the fairness metric enforced during local training.