Saved in:
Bibliographic Details
Main Authors: Lin, Yushen, Chen, Zihan, Ding, Zhiguo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.23315
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909871053471744
author Lin, Yushen
Chen, Zihan
Ding, Zhiguo
author_facet Lin, Yushen
Chen, Zihan
Ding, Zhiguo
contents Federated learning (FL) in wireless networks is limited by straggler delays from unpredictable channel conditions. In this paper, we investigate the pinching-antenna system (PASS), which dynamically 'pinches' the radiator along a dielectric waveguide to shorten the worst links. In synchronous FL (SFL), we prove that PASS shortens the worst-link distance, and it increases the on-time completion probability in asynchronous FL (AFL). Accordingly, SFL exhibits stochastic dominance on round time, while AFL yields explicit latency and participation gains. We then pair physical-layer (PHY)-aware sampling with error-feedback compression and prove that pinching raises the minimum inclusion probability, thus shrinking both the sampling variability and compression-induced floors in a Lyapunov analysis. Simulations demonstrate consistent wall clock speedups and markedly shorter latency tails. By addressing stragglers at their PHY root, PASS complements higher-layer scheduling and accelerates wireless FL in both SFL and AFL.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23315
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pinching-antenna-enabled Federated Learning: Tail Latency, Participation, and Convergence Analysis
Lin, Yushen
Chen, Zihan
Ding, Zhiguo
Information Theory
Federated learning (FL) in wireless networks is limited by straggler delays from unpredictable channel conditions. In this paper, we investigate the pinching-antenna system (PASS), which dynamically 'pinches' the radiator along a dielectric waveguide to shorten the worst links. In synchronous FL (SFL), we prove that PASS shortens the worst-link distance, and it increases the on-time completion probability in asynchronous FL (AFL). Accordingly, SFL exhibits stochastic dominance on round time, while AFL yields explicit latency and participation gains. We then pair physical-layer (PHY)-aware sampling with error-feedback compression and prove that pinching raises the minimum inclusion probability, thus shrinking both the sampling variability and compression-induced floors in a Lyapunov analysis. Simulations demonstrate consistent wall clock speedups and markedly shorter latency tails. By addressing stragglers at their PHY root, PASS complements higher-layer scheduling and accelerates wireless FL in both SFL and AFL.
title Pinching-antenna-enabled Federated Learning: Tail Latency, Participation, and Convergence Analysis
topic Information Theory
url https://arxiv.org/abs/2510.23315