Pinching-antenna-enabled Federated Learning: Tail Latency, Participation, and Convergence Analysis

TL;DR

This paper introduces PASS, a pinching-antenna system that reduces wireless federated learning latency by physically shortening links, improving participation, and convergence, with proven theoretical benefits and simulation validation.

Contribution

It presents PASS as a novel physical-layer solution to mitigate stragglers in wireless FL, enhancing latency, participation, and convergence analysis.

Findings

PASS shortens worst-link distance and improves on-time completion.

PASS increases minimum inclusion probability, reducing sampling variability.

Simulations show significant speedups and shorter latency tails.

Abstract

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.