The longstanding goals of federated learning (FL) require rigorous privacy guarantees and low communication overhead while holding a relatively high model accuracy. However, simultaneously achieving all the goals is extremely challenging. In this paper, we propose a novel framework called hierarchical federated learning (H-FL) to tackle this challenge. Considering the degradation of the model performance due to the statistic heterogeneity of the training data, we devise a runtime distribution reconstruction strategy, which reallocates the clients appropriately and utilizes mediators to rearrange the local training of the clients. In addition, we design a compression-correction mechanism incorporated into H-FL to reduce the communication overhead while not sacrificing the model performance. To further provide privacy guarantees, we introduce differential privacy while performing local training, which injects moderate amount of noise into only part of the complete model. Experimental results show that our H-FL framework achieves the state-of-art performance on different datasets for the real-world image recognition tasks.

本文提出了一种名为分层联邦学习（H-FL）的新框架，通过运行时分布重构策略，利用中介将客户端重新分配并重新安排客户端的本地训练，设计了一种压缩校正机制，同时不牺牲模型性能，降低通信开销，引入局部训练的差分隐私，注入适量的噪声到完整模型的一部分中，从而提供隐私保障，在真实的图像识别任务的不同数据集上实验结果表明，我们的H-FL框架实现了最先进的性能。

H-FL：面向联邦学习的分层通信高效和隐私保护体系结构