A Generalized Hierarchical Federated Learning Framework with Theoretical Guarantees

TL;DR

This paper introduces a multi-layer hierarchical federated learning framework that generalizes existing models to arbitrary network architectures, providing theoretical convergence guarantees and optimizing performance under communication constraints.

Contribution

It proposes the first generalized multi-layer hierarchical FL framework with convergence analysis, layer-specific quantization, and optimal iteration strategies for complex networks.

Findings

Achieves high accuracy under data heterogeneity.

Provides convergence conditions and rates.

Improves performance with optimized parameters.

Abstract

Almost all existing hierarchical federated learning (FL) models are limited to two aggregation layers, restricting scalability and flexibility in complex, large-scale networks. In this work, we propose a Multi-Layer Hierarchical Federated Learning framework (QMLHFL), which appears to be the first study that generalizes hierarchical FL to arbitrary numbers of layers and network architectures through nested aggregation, while employing a layer-specific quantization scheme to meet communication constraints. We develop a comprehensive convergence analysis for QMLHFL and derive a general convergence condition and rate that reveal the effects of key factors, including quantization parameters, hierarchical architecture, and intra-layer iteration counts. Furthermore, we determine the optimal number of intra-layer iterations to maximize the convergence rate while meeting a deadline constraint that accounts for both communication and computation times. Our results show that QMLHFL consistently achieves high learning accuracy, even under high data heterogeneity, and delivers notably improved performance when optimized, compared to using randomly selected values.