We propose an uplink over-the-air aggregation (OAA) method for wireless federated learning (FL) that simultaneously trains multiple models. To maximize the multi-model training convergence rate, we derive an upper bound on the optimality gap of the global model update, and then, formulate an uplink joint transmit-receive beamforming optimization problem to minimize this upper bound. We solve this problem using the block coordinate descent approach, which admits low-complexity closed-form updates. Simulation results show that our proposed multi-model FL with fast OAA substantially outperforms sequentially training multiple models under the conventional single-model approach.
@article{arxiv.2409.00978,
title = {Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning},
author = {Chong Zhang and Min Dong and Ben Liang and Ali Afana and Yahia Ahmed},
journal= {arXiv preprint arXiv:2409.00978},
year = {2024}
}
Comments
5 pages, 5 figures. Accepted by IEEE SPAWC 2024. arXiv admin note: text overlap with arXiv:2312.13424