Device Scheduling in Over-the-Air Federated Learning via Matching Pursuit

Bereyhi A, Vagollari A, Asaad S, Müller R, Gerstacker W, Poor HV (2023)

Publication Type: Journal article

Publication year: 2023

Journal

IEEE Transactions on Signal Processing Institute of Electrical and Electronics Engineers (IEEE)

Pages Range: 1-16

DOI: 10.1109/TSP.2023.3284376

Abstract

This paper develops a class of low-complexity device scheduling algorithms for over-the-air federated learning via the method of matching pursuit. The proposed scheme tracks closely the close-to-optimal performance achieved by difference-of-convex programming, and outperforms significantly the well-known benchmark algorithms based on convex relaxation. Compared to the state-of-the-art, the proposed scheme imposes a drastically lower computational load on the system: for $K$ devices and $N$ antennas at the parameter server, the benchmark complexity scales with $(N^{2}+K)^{3} + N^{6}$ while the complexity of the proposed scheme scales with ${K^{p} N^{q}}$ for some $0 \lt p,q \leq 2$. The efficiency of the proposed scheme is confirmed through the convergence analysis and numerical experiments on CIFAR-10 dataset.

Authors with CRIS profile

Adela Vagollari Lehrstuhl für Digitale Übertragung (IDC) Ralf Müller Professur für Informationsübertragung Wolfgang Gerstacker Lehrstuhl für Digitale Übertragung (IDC)

Involved external institutions

University of Toronto CA Canada (CA) York University CA Canada (CA) Princeton University US United States (USA) (US)

How to cite

APA:

Bereyhi, A., Vagollari, A., Asaad, S., Müller, R., Gerstacker, W., & Poor, H.V. (2023). Device Scheduling in Over-the-Air Federated Learning via Matching Pursuit. IEEE Transactions on Signal Processing, 1-16. https://doi.org/10.1109/TSP.2023.3284376

MLA:

Bereyhi, Ali, et al. "Device Scheduling in Over-the-Air Federated Learning via Matching Pursuit." IEEE Transactions on Signal Processing (2023): 1-16.

BibTeX: Download