查看文章

Federated Learning (FL) has emerged in edge computing to address privacy concerns in mobile networks. It allows the mobile devices to collaboratively train a model while keeping training data where they were generated. However, in practice, it suffers from several issues such as (i) robustness, due to a single point of failure, (ii) latency, as it requires a significant amount of communication resources, and (iii) convergence, due to system and statistical heterogeneity. To cope with these issues, Hierarchical FL (HFL) has been proposed as a promising alternative. HFL adds the edge servers as an intermediate layer for sub-model aggregation, several iterations will be performed before the global aggregation at the cloud server takes place, thus making the overall process more efficient, especially with non-independent and identically distributed (non-IID) data. Moreover, using traditional Artificial Neural Networks …