
HAF-Edge, a novel hierarchical federated learning framework, effectively addresses the challenges of model heterogeneity and non-IID data in edge networks by combining MaxCommon strategy at the cloud level and distance-based weighting aggregation at the edge level.


coremsg

federated-learning-as-a-service-flaas-for-hierarchical-edge-networks-with-heterogeneous-models-a-distance-based-weighting-aggregation-approach


Federated Learning as a Service (FLaaS) for Hierarchical Edge Networks with Heterogeneous Models: A Distance-Based Weighting Aggregation Approach
