Unified Analyses for Hierarchical Federated Learning: Topology Selection under Data Heterogeneity

ICLR 2026 Conference Submission19417 Authors

Keywords: Hierarchical Federated Learning, Convergence Analysis, Heterogeneous Data

Abstract: Hierarchical Federated Learning (HFL) addresses critical scalability limitations in conventional federated learning by incorporating intermediate aggregation layers, yet optimal topology selection across varying data heterogeneity conditions and network conditions remains an open challenge. This paper establishes the first unified convergence framework for all four HFL topologies (Star-Star, Star-Ring, Ring-Star, and Ring-Ring) under non-convex objectives and different intra/inter-group data heterogeneity. Our theoretical analysis reveals three fundamental principles for topology selection: (1) The top-tier aggregation topology exerts greater influence on convergence than the intra-group topology, with ring-based top-tier configurations generally outperforming star-based alternatives; (2) Optimal topology strongly depends on client grouping characteristics, where Ring-Star excels with numerous small groups while Star-Ring is superior for large, client-dense clusters; and (3) Inter-group heterogeneity dominates convergence dynamics across all topologies, necessitating clustering strategies that minimize inter-group divergence. Extensive experiments on CIFAR-10/CINIC-10/Fashion-MNIST with ResNet-18/VGG-9/ResNet-10 validate these insights, and provide practitioners with theoretically grounded guidance for HFL system design in real-world deployments.

Primary Area: optimization

Submission Number: 19417