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

Ali Bereyhi, Adela Vagollari, Saba Asaad, Ralf R. Muller, Wolfgang Gerstacker, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


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 (N2+K) 3+ N6 while the complexity of the proposed scheme scales with Kp Nq for some 0 < p,q 2. The efficiency of the proposed scheme is confirmed through the convergence analysis and numerical experiments on CIFAR-10 dataset.

Original languageEnglish (US)
Pages (from-to)2188-2203
Number of pages16
JournalIEEE Transactions on Signal Processing
StatePublished - 2023
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering


  • Device scheduling
  • federated learning
  • matching pursuit
  • over-the-air computation


Dive into the research topics of 'Device Scheduling in Over-the-Air Federated Learning Via Matching Pursuit'. Together they form a unique fingerprint.

Cite this