SPARK: A Scalable Peer-to-Peer Asynchronous Resilient Framework for Federated Learning in Non-Terrestrial Networks

Yu, G; He, Y; Dutkiewicz, E; Senanayake, B; Attygalle, M

SPARK: A Scalable Peer-to-Peer Asynchronous Resilient Framework for Federated Learning in Non-Terrestrial Networks

Yu, G

He, Y

Dutkiewicz, E

Senanayake, B Attygalle, M

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE TRANSACTIONS ON MACHINE LEARNING IN COMMUNICATIONS AND NETWORKING, 2025, 3, (99), pp. 1092-1107
Issue Date:: 2025

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (2.58 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Yu, G https://orcid.org/0000-0002-6111-1607
dc.contributor.author	He, Y https://orcid.org/0000-0003-1603-9375
dc.contributor.author	Dutkiewicz, E https://orcid.org/0000-0002-4268-9286
dc.contributor.author	Senanayake, B
dc.contributor.author	Attygalle, M
dc.date.accessioned	2025-12-22T06:03:47Z
dc.date.available	2025-12-22T06:03:47Z
dc.date.issued	2025
dc.identifier.citation	IEEE TRANSACTIONS ON MACHINE LEARNING IN COMMUNICATIONS AND NETWORKING, 2025, 3, (99), pp. 1092-1107
dc.identifier.issn	2831-316X
dc.identifier.issn	2831-316X
dc.identifier.uri	http://hdl.handle.net/10453/191107
dc.description.abstract	Federated Learning (FL) faces significant challenges when applied in 6G (sixth-generation wireless technology) Non-Terrestrial Network (NTN) environments, including heterogeneous interference, stringent requirements for real-time model responsiveness, and limited ability to collect comprehensive datasets due to the absence of a global network view. In this paper, we propose SPARK, a novel framework designed to enable a fully decentralized FL process tailored for NTN. By leveraging a Directed acyclic graph (DAG)-based architecture, SPARK addresses the unique demands of NTN through asynchronous updates, localized learning prioritization, and adaptive aggregation strategies, ensuring robust performance under dynamic and constrained conditions. Extensive experiments demonstrate that SPARK outperforms other FL frameworks and effectively addresses the key challenges of NTN-based FL through its asynchronous design–ensuring resilience under communication delays, enhancing responsiveness via timely local updates, and improving coverage through altitude-aware aggregation that leverages diverse, high-altitude knowledge.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE TRANSACTIONS ON MACHINE LEARNING IN COMMUNICATIONS AND NETWORKING
dc.relation.isbasedon	10.1109/TMLCN.2025.3617883
dc.rights	info:eu-repo/semantics/openAccess
dc.title	SPARK: A Scalable Peer-to-Peer Asynchronous Resilient Framework for Federated Learning in Non-Terrestrial Networks
dc.type	Journal Article
utslib.citation.volume	3
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Global Big Data Technologies Centre (GBDTC)
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2025-12-22T06:03:40Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	3
utslib.citation.issue	99

Abstract:

Federated Learning (FL) faces significant challenges when applied in 6G (sixth-generation wireless technology) Non-Terrestrial Network (NTN) environments, including heterogeneous interference, stringent requirements for real-time model responsiveness, and limited ability to collect comprehensive datasets due to the absence of a global network view. In this paper, we propose SPARK, a novel framework designed to enable a fully decentralized FL process tailored for NTN. By leveraging a Directed acyclic graph (DAG)-based architecture, SPARK addresses the unique demands of NTN through asynchronous updates, localized learning prioritization, and adaptive aggregation strategies, ensuring robust performance under dynamic and constrained conditions. Extensive experiments demonstrate that SPARK outperforms other FL frameworks and effectively addresses the key challenges of NTN-based FL through its asynchronous design–ensuring resilience under communication delays, enhancing responsiveness via timely local updates, and improving coverage through altitude-aware aggregation that leverages diverse, high-altitude knowledge.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/191107