University of Oulu

S. Savazzi, V. Rampa, S. Kianoush and M. Bennis, "On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning," 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Kyoto, Japan, 2022, pp. 1431-1437, doi: 10.1109/PIMRC54779.2022.9977688

On the energy and communication efficiency tradeoffs in federated and multi-task learning

Saved in:
Author: Savazzi, Stefano1; Rampa, Vittorio1; Kianoush, Sanaz1;
Organizations: 1Consiglio Nazionale delle Ricerche (CNR), IEIIT institute, Milano
2Centre for Wireless Communications University of Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 3.4 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2022
Publish Date: 2023-02-10


Recent advances in Federated Learning (FL) have paved the way towards the design of novel strategies for solving multiple learning tasks simultaneously, by leveraging cooperation among networked devices. Multi-Task Learning (MTL) exploits relevant commonalities across tasks to improve efficiency compared with traditional transfer learning approaches. By learning multiple tasks jointly, significant reduction in terms of energy footprints can be obtained. This article provides a first look into the energy costs of MTL processes driven by the Model-Agnostic Meta-Learning (MAML) paradigm and implemented in distributed wireless networks. The paper targets a clustered multi-task network setup where autonomous agents learn different but related tasks. The MTL process is carried out in two stages: the optimization of a meta-model that can be quickly adapted to learn new tasks, and a task-specific model adaptation stage where the learned meta-model is transferred to agents and tailored for a specific task. This work analyzes the main factors that influence the MTL energy balance by considering a multi-task Reinforcement Learning (RL) setup in a robotized environment. Results show that the MAML method can reduce the energy bill by at least 2 × compared with traditional approaches without inductive transfer. Moreover, it is shown that the optimal energy balance in wireless networks depends on uplink/downlink and sidelink communication efficiencies.

see all

Series: IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications workshops
ISSN: 2166-9570
ISSN-E: 2166-9589
ISSN-L: 2166-9570
ISBN: 978-1-6654-8053-6
ISBN Print: 978-1-6654-8054-3
Pages: 1431 - 1437
DOI: 10.1109/PIMRC54779.2022.9977688
Host publication: 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)
Conference: IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications
Type of Publication: A4 Article in conference proceedings
Field of Science: 213 Electronic, automation and communications engineering, electronics
Copyright information: © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.