EUVIMEDEUVIMED entdecken
Crossref

Breakout Local Search for Load-Balanced Federated Learning in Multi-BS Networks

Mina Kato, Xun Yuan, Tiago Koketsu Rodrigues, Fengxiao Tang, Ming Zhao, Nei Kato

IEEE Transactions on Emerging Topics in Computing · 2026-01 · 14 (1) · 364-376

DOI: 10.1109/tetc.2026.3667101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Emerging Topics in Computing, 2026-01. Verfasst von Mina Kato und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hunan Provincial Natural Science Foundation, Changsha Municipal Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) relies on timely participation of multiple devices, yet the round time is often dominated by the slowest user under heterogeneous wireless conditions. In multi-base-station (multi-BS) environments with nonlinear concurrent uplink and diverse backhaul capacities, selecting an appropriate set of participants becomes a challenging combinatorial optimization problem. We cast the problem as a round-time–centric optimization with reference-latency-scaled fairness penalties to enforce diversity, cohort size, and BS load balance. To solve it efficiently, we propose a Breakout Local Search (BLS) solver that couples k-opt local refinement with approximate screening and adaptive three-mode perturbations under a wall-clock budget, enabling efficient exploration–exploitation. Extensive simulations under hotspot and throttled-backhaul scenarios show that the proposed method reduces round time by 80–90% compared with particle swarm optimization (PSO) and Random, and by 29–75% compared with Greedy and simulated annealing (SA), while lowering the overall objective by 80–84% relative to PSO and Random and 50–67% relative to Greedy and SA, across various diversity weights and target participant sizes. The results highlight the effectiveness of our BLS method in FL participant selection under realistic and difficult network conditions.

Förderung

  • National Natural Science Foundation of China
  • Hunan Provincial Natural Science Foundation
  • Changsha Municipal Natural Science Foundation
  • High Performance Computing Center of Central South University

Zitieren

APA

Kato, M., Yuan, X., Rodrigues, T. K., Tang, F., Zhao, M., & Kato, N. (2026). Breakout Local Search for Load-Balanced Federated Learning in Multi-BS Networks. IEEE Transactions on Emerging Topics in Computing, 14(1), 364-376. https://doi.org/10.1109/tetc.2026.3667101

Vancouver

Kato M, Yuan X, Rodrigues TK, Tang F, Zhao M, Kato N. Breakout Local Search for Load-Balanced Federated Learning in Multi-BS Networks. IEEE Transactions on Emerging Topics in Computing. 2026;14(1):364-376. doi:10.1109/tetc.2026.3667101

BibTeX
@article{Kato2026,
  author = {Kato, Mina and Yuan, Xun and Rodrigues, Tiago Koketsu and Tang, Fengxiao and Zhao, Ming and Kato, Nei},
  title = {Breakout Local Search for Load-Balanced Federated Learning in Multi-BS Networks},
  journal = {IEEE Transactions on Emerging Topics in Computing},
  year = {2026},
  volume = {14},
  number = {1},
  pages = {364--376},
  doi = {10.1109/tetc.2026.3667101}
}
Kostenlos starten →