EUVIMEDEUVIMED entdecken
Crossref

Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks

Xiaoyu He, Weicai Li, Tiejun Lv, Xi Yu

IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 6841-6855

DOI: 10.1109/tccn.2026.3676037 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Xiaoyu He und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Decentralized federated learning (D-FL) enables privacy-preserving training without a central server, but multi-hop model exchanges and aggregation are often bottlenecked by communication resource constraints. To address this issue, we propose a joint routing-and-pruning framework that optimizes routing paths and pruning rates to keep communication latency within prescribed limits. We analyze how the sum of model biases across all clients affects the convergence bound of D-FL, and formulate an optimization that maximizes the model retention rate to reduce these biases under communication constraints. Further analysis shows that each client’s model retention rate is path-dependent, which reduces the original problem to a routing optimization. Leveraging this insight, we develop a routing algorithm that selects latency-efficient transmission paths, allowing more parameters to be delivered within the time budget and thereby improving D-FL convergence. Simulations show that, compared with unpruned systems, the proposed framework reduces average transmission latency by 27.8% and improves testing accuracy by about 12%; relative to standard benchmark routing algorithms, the proposed routing method further improves accuracy by roughly 8%.

Zitieren

APA

He, X., Li, W., Lv, T., & Yu, X. (2026). Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks. IEEE Transactions on Cognitive Communications and Networking, 12, 6841-6855. https://doi.org/10.1109/tccn.2026.3676037

Vancouver

He X, Li W, Lv T, Yu X. Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks. IEEE Transactions on Cognitive Communications and Networking. 2026;12:6841-6855. doi:10.1109/tccn.2026.3676037

BibTeX
@article{He2026,
  author = {He, Xiaoyu and Li, Weicai and Lv, Tiejun and Yu, Xi},
  title = {Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2026},
  volume = {12},
  pages = {6841--6855},
  doi = {10.1109/tccn.2026.3676037}
}
Kostenlos starten →