EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tail-Latency-Aware Federated Learning with Pinching Antenna: Latency, Participation, and Placement

Yushen Lin, Zhiguo Ding

Entropy · 18.03.2026 · 28 (3) · 341

DOI: 10.3390/e28030341 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 18.03.2026. Verfasst von Yushen Lin und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Electronic Engineering, The University of Manchester, Manchester M13 9PL, UK. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Straggler synchronization is a dominant wall-clock bottleneck in synchronous wireless federated learning (FL). Under non-IID data, however, aggressively sampling only fast clients may significantly slow convergence due to statistical heterogeneity. This paper studies PASS-enabled FL, where a radiating pinching antenna (PA) can be activated at an arbitrary position along a dielectric waveguide to reshape uplink latencies. We consider a joint optimization of PA placement and client participation to minimize a proxy for time-to-accuracy, coupling the exact expected maximum round latency via order statistics with a heterogeneity-aware statistical-efficiency proxy. We derive first-order optimality conditions that reveal an explicit tail-latency premium in the KKT recursion, quantifying how latency gaps are amplified by maximum-order-statistic synchronization. Under a latency-class structure, we obtain a within-class square-root sampling law and establish a two-class phase transition where slow-class participation collapses under an explicit heterogeneity-threshold condition as the per-round sample size grows. For PA placement, we prove a piecewise envelope-derivative characterization and provide an exact breakpoint-and-root candidate-enumeration procedure. Simulation results validate the structural findings and show that PASS enables more eligible participation, yielding higher wall-clock accuracy.

Schlagwörter

Stichwörter der Autor:innen

antenna placementfederated learning (FL)non-IIDpinching antennastragglerstail latency

Autor:innen und Institutionen

  • Department of Electrical and Electronic Engineering, The University of Manchester, Manchester M13 9PL, UK.
  • School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore.

Zitieren

APA

Lin, Y., & Ding, Z. (2026). Tail-Latency-Aware Federated Learning with Pinching Antenna: Latency, Participation, and Placement. Entropy, 28(3), 341. https://doi.org/10.3390/e28030341

Vancouver

Lin Y, Ding Z. Tail-Latency-Aware Federated Learning with Pinching Antenna: Latency, Participation, and Placement. Entropy. 2026;28(3):341. doi:10.3390/e28030341

BibTeX
@article{Lin2026,
  author = {Lin, Yushen and Ding, Zhiguo},
  title = {Tail-Latency-Aware Federated Learning with Pinching Antenna: Latency, Participation, and Placement},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {3},
  pages = {341},
  doi = {10.3390/e28030341}
}
Kostenlos starten →