EUVIMEDEUVIMED entdecken
Crossref

FedTCTF: Tensor Completion-Based Federated Learning for Device Heterogeneity

Cangming Liang, Wei Liang, Yuxiang Chen, Kuanching Li, Albert Y. Zomaya

IEEE Transactions on Sustainable Computing · 2025-11 · 10 (6) · 1227-1239

DOI: 10.1109/tsusc.2025.3614896 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Sustainable Computing, 2025-11. Verfasst von Cangming Liang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Joint Key Project of National Natural Science Foundation of China, National Natural Science Foundation of China, Hunan Provincial Key Research and Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the advancement of Artificial Intelligence of Things (AIoT) systems, edge devices are increasingly capable of participating in Federated Learning (FL) by collaboratively training a global model while preserving data privacy. However, the low bit-width and limited storage capacity of edge devices often degrade global model accuracy, leading traditional FL frameworks to resource waste. To address this issue and enhance edge device utilization, we propose FedTCTF, an innovative framework that integrates optimized tensor completion with a novel traversal-based Layer-Wise Model Partitioning strategy. Our approach tackles both bit-width heterogeneity and capacity constraints through two key innovations: (1) A bit-width-aware tensor completion method using adaptive Tucker and CP decomposition to align parameter precision across devices; (2) A layer-wise dynamic sub-model extraction mechanism that systematically cycles through all parts of the global model via a traversal window. Specifically, the server dynamically extracts sub-models from the global model based on device capacities, with the traversal window advancing layer-by-layer in each training round to extract layers not covered in the previous rounds, ensuring resource-constrained devices evenly train the full model. Experimental results demonstrate FedTCTF’s superiority: It achieves up to 20.77% higher accuracy on CIFAR-10 with ResNet18 compared to state-of-the-art methods, and consistently outperforms all baselines on NLP tasks, including AGNews and StackOverflow with Transformer, particularly excelling when 80% of clients are low-capacity devices. By enabling comprehensive device participation through precision recovery and uniform model coverage, FedTCTF establishes a sustainable learning paradigm for AIoT ecosystems.

Förderung

  • Joint Key Project of National Natural Science Foundation of China
  • National Natural Science Foundation of China
  • Hunan Provincial Key Research and Development Program
  • Natural Science Foundation of Hunan Province
  • Scientific Research Fund of Hunan Provincial Education Department

Zitieren

APA

Liang, C., Liang, W., Chen, Y., Li, K., & Zomaya, A. Y. (2025). FedTCTF: Tensor Completion-Based Federated Learning for Device Heterogeneity. IEEE Transactions on Sustainable Computing, 10(6), 1227-1239. https://doi.org/10.1109/tsusc.2025.3614896

Vancouver

Liang C, Liang W, Chen Y, Li K, Zomaya AY. FedTCTF: Tensor Completion-Based Federated Learning for Device Heterogeneity. IEEE Transactions on Sustainable Computing. 2025;10(6):1227-1239. doi:10.1109/tsusc.2025.3614896

BibTeX
@article{Liang2025,
  author = {Liang, Cangming and Liang, Wei and Chen, Yuxiang and Li, Kuanching and Zomaya, Albert Y.},
  title = {FedTCTF: Tensor Completion-Based Federated Learning for Device Heterogeneity},
  journal = {IEEE Transactions on Sustainable Computing},
  year = {2025},
  volume = {10},
  number = {6},
  pages = {1227--1239},
  doi = {10.1109/tsusc.2025.3614896}
}
Kostenlos starten →