Hierarchical Federated Learning in Wireless Networks: Pruning Tackles Bandwidth Scarcity and System Heterogeneity

TL;DR

This paper introduces a hierarchical federated learning framework with model pruning for wireless networks, optimizing communication and computation to address bandwidth and heterogeneity constraints, validated through extensive simulations.

Contribution

It proposes a novel pruning-enabled hierarchical federated learning method with convergence analysis and joint optimization of system parameters under practical constraints.

Findings

Improved test accuracy and reduced training time.

Significant energy savings and bandwidth efficiency.

Effective handling of system heterogeneity.

Abstract

While a practical wireless network has many tiers where end users do not directly communicate with the central server, the users' devices have limited computation and battery powers, and the serving base station (BS) has a fixed bandwidth. Owing to these practical constraints and system models, this paper leverages model pruning and proposes a pruning-enabled hierarchical federated learning (PHFL) in heterogeneous networks (HetNets). We first derive an upper bound of the convergence rate that clearly demonstrates the impact of the model pruning and wireless communications between the clients and the associated BS. Then we jointly optimize the model pruning ratio, central processing unit (CPU) frequency and transmission power of the clients in order to minimize the controllable terms of the convergence bound under strict delay and energy constraints. However, since the original problem is not convex, we perform successive convex approximation (SCA) and jointly optimize the parameters for the relaxed convex problem. Through extensive simulation, we validate the effectiveness of our proposed PHFL algorithm in terms of test accuracy, wall clock time, energy consumption and bandwidth requirement.