Federated Learning (FL) is a novel distributed machine learning approach to leverage data from Internet of Things (IoT) devices while maintaining data privacy. However, the current FL algorithms face the challenges of non-independent and identically distributed (non-IID) data, which causes high communication costs and model accuracy declines. To address the statistical imbalances in FL, we propose a clustered data sharing framework which spares the partial data from cluster heads to credible associates through device-to-device (D2D) communication. Moreover, aiming at diluting the data skew on nodes, we formulate the joint clustering and data sharing problem based on the privacy-preserving constrained graph. To tackle the serious coupling of decisions on the graph, we devise a distribution-based adaptive clustering algorithm (DACA) basing on three deductive cluster-forming conditions, which ensures the maximum yield of data sharing. The experiments show that the proposed framework facilitates FL on non-IID datasets with better convergence and model accuracy under a limited communication environment.

翻译：联邦学习（FL）作为一种新型分布式机器学习方法，能够利用物联网（IoT）设备数据同时保护数据隐私。然而，当前FL算法面临非独立同分布（non-IID）数据带来的挑战，导致通信成本升高和模型精度下降。针对FL中的统计不均衡问题，本文提出一种聚类数据共享框架，通过设备到设备（D2D）通信将簇头节点的部分数据分配给可信关联节点。为稀释节点间的数据偏斜，我们基于隐私保护约束图构建联合聚类与数据共享问题。为解决图中决策的强耦合性，基于三条推导出的聚类形成条件，设计了一种基于分布的自适应聚类算法（DACA），确保数据共享收益最大化。实验表明，在有限通信环境下，所提框架能促进non-IID数据集上的联邦学习，实现更优的收敛性与模型精度。