Matching Pursuit Based Scheduling for Over-the-Air Federated Learning

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 poses a drastically lower computational load on the system: For devices and antennas at the parameter server, the benchmark complexity scales with while the complexity of the proposed scheme scales with for some . The efficiency of the proposed scheme is confirmed via numerical experiments on the CIFAR-10 dataset.
View on arXivComments on this paper