Hierarchical Split Federated Learning: Convergence Analysis and System Optimization

TL;DR

This paper introduces a hierarchical split federated learning framework for multi-tier systems, providing convergence analysis and an optimization algorithm to improve learning performance on resource-limited edge devices.

Contribution

It proposes the HSFL framework, derives its convergence bounds, and develops an iterative algorithm for joint model splitting and aggregation optimization.

Findings

The algorithm effectively optimizes model splitting and aggregation in multi-tier systems.

Simulation results show improved convergence and performance.

The framework adapts to various multi-tier system configurations.

Abstract

As AI models expand in size, it has become increasingly challenging to deploy federated learning (FL) on resource-constrained edge devices. To tackle this issue, split federated learning (SFL) has emerged as an FL framework with reduced workload on edge devices via model splitting; it has received extensive attention from the research community in recent years. Nevertheless, most prior works on SFL focus only on a two-tier architecture without harnessing multi-tier cloudedge computing resources. In this paper, we intend to analyze and optimize the learning performance of SFL under multi-tier systems. Specifically, we propose the hierarchical SFL (HSFL) framework and derive its convergence bound. Based on the theoretical results, we formulate a joint optimization problem for model splitting (MS) and model aggregation (MA). To solve this rather hard problem, we then decompose it into MS and MA subproblems that can be solved via an iterative descending algorithm. Simulation results demonstrate that the tailored algorithm can effectively optimize MS and MA for SFL within virtually any multi-tier system.