Joint topology and beamforming optimization for decentralized federated learning

Author Identifier (ORCID)

Wei Ni: https://orcid.org/0000-0002-4933-594X

Abstract

Decentralized Federated Learning (DFL) enables collaborative model training without central coordination. However, DFL faces challenges in dynamic networks, where existing methods struggle to balance consensus rate and communication efficiency, while overlooking practical issues such as topology variation. This paper presents Dynamic AirComp-enabled DFL (DA-DFL), a novel framework that integrates over-the-air computation (AirComp) with the BASE-GRAPH consensus algorithm for efficient DFL over dynamic topologies. The convergence analysis for DA-DFL under dynamic settings is conducted to reveal the influence of the consensus period and communication errors. We define communication overhead metrics, and jointly optimize transceiver beamformers and dynamic topologies. A topology matching algorithm is developed to reduce communication overhead by aligning logical and physical topologies. Experiments show significant gains of DA-DFL in communication efficiency, e.g., reducing communication links and distances by up to 42% and 50%, respectively, compared to benchmarks.

Keywords

Consensus problem, decentralized federated learning, dynamic topology, over-the-air computation (AirComp)

Document Type

Journal Article

Date of Publication

1-1-2026

Volume

25

Publication Title

IEEE Transactions on Wireless Communications

Publisher

IEEE

School

School of Engineering

Funders

National Natural Science Foundation of China (B62271352, 42171404) / Fundamental Research Funds for the Central Universities (22120250094)

Comments

Feng, H., Wang, R., Liu, E., Ni, W., Niyato, D., & Jamalipour, A. (2026). Joint topology and beamforming optimization for decentralized federated learning. IEEE Transactions on Wireless Communications, 25, 12945–12961. https://doi.org/10.1109/TWC.2026.3667951

Copyright

subscription content

First Page

12945

Last Page

12961

Share

 
COinS
 

Link to publisher version (DOI)

10.1109/TWC.2026.3667951