Skip to main navigation Skip to search Skip to main content

Over-the-Air Federated Learning via Second-Order Optimization

  • Peng Yang
  • , Yuning Jiang
  • , Ting Wang*
  • , Yong Zhou
  • , Yuanming Shi
  • , Colin N. Jones
  • *Corresponding author for this work
  • East China Normal University
  • Swiss Federal Institute of Technology Lausanne
  • ShanghaiTech University

Research output: Contribution to journalArticlepeer-review

Abstract

Federated learning (FL) is a promising learning paradigm that can tackle the increasingly prominent isolated data islands problem while keeping users' data locally with privacy and security guarantees. However, FL could result in task-oriented data traffic flows over wireless networks with limited radio resources. To design communication-efficient FL, most of the existing studies employ the first-order federated optimization approach that has a slow convergence rate. This however results in excessive communication rounds for local model updates between the edge devices and edge server. To address this issue, in this paper, we instead propose a novel over-the-air second-order federated optimization algorithm to simultaneously reduce the communication rounds and enable low-latency global model aggregation. This is achieved by exploiting the waveform superposition property of a multi-access channel to implement the distributed second-order optimization algorithm over wireless networks. The convergence behavior of the proposed algorithm is further characterized, which reveals a linear-quadratic convergence rate with an accumulative error term in each iteration. We thus propose a system optimization approach to minimize the accumulated error gap by joint device selection and beamforming design. Numerical results demonstrate the system and communication efficiency compared with the state-of-the-art approaches.

Original languageEnglish
Pages (from-to)10560-10575
Number of pages16
JournalIEEE Transactions on Wireless Communications
Volume21
Issue number12
DOIs
StatePublished - 1 Dec 2022

Keywords

  • Federated learning
  • over-the-air computation
  • second-order optimization method

Fingerprint

Dive into the research topics of 'Over-the-Air Federated Learning via Second-Order Optimization'. Together they form a unique fingerprint.

Cite this