AoI-Driven Client Scheduling for Federated Learning: A Lagrangian Index Approach

Ma M, Wong VW, Schober R (2023)


Publication Type: Conference contribution

Publication year: 2023

Journal

Publisher: Institute of Electrical and Electronics Engineers Inc.

Book Volume: 2023-May

Pages Range: 3958-3963

Conference Proceedings Title: IEEE International Conference on Communications

Event location: Rome, ITA

ISBN: 9781538674628

DOI: 10.1109/ICC45041.2023.10279272

Abstract

Federated learning (FL) is a distributed learning framework where clients jointly train a global model without sharing their local datasets. In randomized client sampling, a subset of clients are uniformly chosen to participate in training in each communication round of FL. Recent research has shown that by jointly considering the age of information (AoI) and channel state information (CSI) of each client, the convergence of FL can be improved. In this paper, we formulate a joint AoI and CSI-based client scheduling problem as a constrained Markov decision process. We propose a low-complexity and scalable algorithm based on the Lagrangian index approach. Simulation results show that the proposed Lagrangian index-based approach achieves near-optimal performance. For FL tasks with the CIFAR-10 dataset, our results show that the proposed algorithm can speed up the convergence of FL by 40%, by reducing the duration of uplink transmission, when compared with two state-of-the-art FL algorithms.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Ma, M., Wong, V.W., & Schober, R. (2023). AoI-Driven Client Scheduling for Federated Learning: A Lagrangian Index Approach. In Michele Zorzi, Meixia Tao, Walid Saad (Eds.), IEEE International Conference on Communications (pp. 3958-3963). Rome, ITA: Institute of Electrical and Electronics Engineers Inc..

MLA:

Ma, Manyou, Vincent W.S. Wong, and Robert Schober. "AoI-Driven Client Scheduling for Federated Learning: A Lagrangian Index Approach." Proceedings of the 2023 IEEE International Conference on Communications, ICC 2023, Rome, ITA Ed. Michele Zorzi, Meixia Tao, Walid Saad, Institute of Electrical and Electronics Engineers Inc., 2023. 3958-3963.

BibTeX: Download