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.

翻译：无线网络中的联邦学习（FL）受限于不可预测信道条件导致的掉队者延迟。本文研究夹捏天线系统（PASS），该系统沿介质波导动态“夹捏”辐射体以缩短最差链路。在同步联邦学习（SFL）中，我们证明PASS能缩短最差链路距离；在异步联邦学习（AFL）中，则能提高准时完成概率。相应地，SFL在轮次时间上呈现随机占优性，而AFL则实现显式的延迟与参与度增益。我们进一步将物理层感知采样与误差反馈压缩相结合，证明夹捏操作能提升最小包含概率，从而在Lyapunov分析中同时降低采样变异性和压缩引起的误差平台。仿真实验显示系统获得持续的实际时间加速和显著缩短的延迟尾部。通过从物理层根源解决掉队者问题，PASS可补充高层调度机制，在SFL与AFL中共同加速无线联邦学习。