English

Joint Downlink-Uplink Beamforming for Wireless Multi-Antenna Federated Learning

Information Theory 2023-07-04 v1 math.IT

Abstract

We study joint downlink-uplink beamforming design for wireless federated learning (FL) with a multi-antenna base station. Considering analog transmission over noisy channels and uplink over-the-air aggregation, we derive the global model update expression over communication rounds. We then obtain an upper bound on the expected global loss function, capturing the downlink and uplink beamforming and receiver noise effect. We propose a low-complexity joint beamforming algorithm to minimize this upper bound, which employs alternating optimization to breakdown the problem into three subproblems, each solved via closed-form gradient updates. Simulation under practical wireless system setup shows that our proposed joint beamforming design solution substantially outperforms the conventional separate-link design approach and nearly attains the performance of ideal FL with error-free communication links.

Keywords

Cite

@article{arxiv.2307.00315,
  title  = {Joint Downlink-Uplink Beamforming for Wireless Multi-Antenna Federated Learning},
  author = {Chong Zhang and Min Dong and Ben Liang and Ali Afana and Yahia Ahmed},
  journal= {arXiv preprint arXiv:2307.00315},
  year   = {2023}
}

Comments

8 pages, 3 figures. Accepted by International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt), 2023

R2 v1 2026-06-28T11:19:41.264Z