EUVIMEDEUVIMED entdecken
Crossref

Effective UAV-Aided Asynchronous Decentralized Federated Learning With Distributed, Adaptive and Energy-Aware Gradient Sparsification

Alia Asheralieva, Dusit Niyato

IEEE Internet of Things Journal · 15.07.2025 · 12 (14) · 27461-27480

DOI: 10.1109/jiot.2025.3565005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 15.07.2025. Verfasst von Alia Asheralieva und 1 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: National Research Foundation Singapore, Infocomm Media Development Authority under its Future Communications Research and Development Programme, Singapore Ministry of Education (MOE) Tier 1.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We consider decentralized federated learning (DFL) in unpiloted aerial vehicle (UAV) networks where UAVs collaboratively train their machine learning (ML) models in a serverless peer-to-peer manner without sharing local data. We focus on three challenges affecting the performance and feasibility of UAV-aided DFL: 1) communication inefficiency; 2) dynamics, heterogeneity and energy constraints of UAV networks; and 3) high synchronization overheads. To address these challenges, we propose an asynchronous DFL (A-DFL) model for UAV networks and design a novel distributed, adaptive and energy-aware model compression method based on the gradient sparsification. In this method, UAVs communicate asynchronously and apply the time-varying and nonidentical compression parameters to adjust to a dynamic, heterogeneous environment. This reduces synchronization overheads and improves the communication efficiency given the strict battery constraints of UAVs. We show that our method can be formulated as a Markov potential game where the UAVs act as the players which decide on their compression parameters and the number of training data samples used for model updates. We prove that our game admits a dominant pure-strategy Nash equilibrium (NE) that maximizes its potential function and develop a new sparsified A-DFL algorithm enabling every UAV to reach its dominant strategy independently, in polynomial time. We then prove that the proposed algorithm converges to the Pareto-optimal NE representing the most efficient solution of our game. Using extensive simulations, we verify that our algorithm outperforms the state-of-the-art methods in terms of the key evaluation metrics of DFL.

Förderung

  • National Research Foundation Singapore
  • Infocomm Media Development Authority under its Future Communications Research and Development Programme
  • Singapore Ministry of Education (MOE) Tier 1
  • NTU Centre for Computational Technologies in Finance
  • RIE2025 Industry Alignment Fund—Industry Collaboration Projects
  • administered by A*STAR, as well as supported by the Alibaba Group
  • NTU Singapore through Alibaba-NTU Global e-Sustainability CorpLab

Zitieren

APA

Asheralieva, A., & Niyato, D. (2025). Effective UAV-Aided Asynchronous Decentralized Federated Learning With Distributed, Adaptive and Energy-Aware Gradient Sparsification. IEEE Internet of Things Journal, 12(14), 27461-27480. https://doi.org/10.1109/jiot.2025.3565005

Vancouver

Asheralieva A, Niyato D. Effective UAV-Aided Asynchronous Decentralized Federated Learning With Distributed, Adaptive and Energy-Aware Gradient Sparsification. IEEE Internet of Things Journal. 2025;12(14):27461-27480. doi:10.1109/jiot.2025.3565005

BibTeX
@article{Asheralieva2025,
  author = {Asheralieva, Alia and Niyato, Dusit},
  title = {Effective UAV-Aided Asynchronous Decentralized Federated Learning With Distributed, Adaptive and Energy-Aware Gradient Sparsification},
  journal = {IEEE Internet of Things Journal},
  year = {2025},
  volume = {12},
  number = {14},
  pages = {27461--27480},
  doi = {10.1109/jiot.2025.3565005}
}
Kostenlos starten →