Litcius/Paper detail

Hierarchical Federated Learning With Momentum Acceleration in Multi-Tier Networks

Zhengjie Yang, Sen Fu, Wei Bao, Dong Yuan, Albert Y. Zomaya

2023IEEE Transactions on Parallel and Distributed Systems14 citationsDOI

Abstract

In this article, we propose Hierarchical Federated Learning with Momentum Acceleration (HierMo), a three-tier worker-edge-cloud federated learning algorithm that applies momentum for training acceleration. Momentum is calculated and aggregated in the three tiers. We provide convergence analysis for HierMo, showing a convergence rate of <inline-formula><tex-math notation="LaTeX">$\mathcal {O}(\frac{1}{T})$</tex-math></inline-formula> . In the analysis, we develop a new approach to characterize model aggregation, momentum aggregation, and their interactions. Based on this result, we prove that HierMo achieves a tighter convergence upper bound compared with HierFAVG without momentum. We also propose HierOPT, which optimizes the aggregation periods (worker-edge and edge-cloud aggregation periods) to minimize the loss given a limited training time. By conducting the experiment, we verify that HierMo outperforms existing mainstream benchmarks under a wide range of settings. In addition, HierOPT can achieve a near-optimal performance when we test HierMo under different aggregation periods.

Topics & Concepts

Momentum (technical analysis)AccelerationComputer scienceConvergence (economics)Enhanced Data Rates for GSM EvolutionEdge deviceMainstreamRange (aeronautics)Cloud computingTheoretical computer sciencePhysicsArtificial intelligenceClassical mechanicsEngineeringFinanceAerospace engineeringEconomicsOperating systemPhilosophyTheologyEconomic growthPrivacy-Preserving Technologies in DataMobile Crowdsensing and CrowdsourcingStochastic Gradient Optimization Techniques
Hierarchical Federated Learning With Momentum Acceleration in Multi-Tier Networks | Litcius