Wireless Hierarchical Federated Aggregation Weights Design with Loss-Based-Heterogeneity

Hierarchical federated learning (HFL) in wireless networks significantly saves communication resources thanks to edge aggregation in edge mobile computing (MEC) servers. Considering the spatially correlated data in wireless networks, in this paper, we analyze the performance of HFL with hybrid data distributions, i.e. intra-MEC independent and identically distributed (IID) and inter-MEC non-IID data samples. We also derive the performance impacts of data heterogeneity and global aggregation interval. Based on our theoretical results, we further propose a novel aggregation weights design with loss-based heterogeneity to accelerate the training of HFL and improve learning accuracy. Our simulations verify the theoretical results and demonstrate the performance gain achieved by the proposed aggregation weights design. Moreover, we find that the performance gain of the proposed aggregation weights design is higher in a high-heterogeneity scenario than in a low-heterogeneity one.