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 the expected time-to-accuracy, coupling the exact expected maximum round latency via order statistics with a heterogeneity-aware convergence factor. 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 verify the theoretical findings and show that PASS enables more eligible participation, yielding higher wall-clock accuracy.

翻译：在同步无线联邦学习（FL）中，掉队者同步是挂钟时间的主要瓶颈。然而，在非独立同分布数据下，仅激进地采样快速客户端可能因统计异构性而显著减缓收敛速度。本文研究了PASS赋能的联邦学习，其中辐射夹持天线（PA）可沿介质波导在任意位置激活以重塑上行链路延迟。我们考虑联合优化PA部署与客户端参与，以最小化期望达到精度时间，通过顺序统计量将精确的期望最大轮次延迟与异构感知收敛因子相耦合。我们推导出一阶最优性条件，揭示了KKT递归中显式的尾部延迟溢价，量化了延迟差距如何通过最大顺序统计量同步被放大。在延迟类结构下，我们得到了类内平方根采样定律，并建立了一个两类相变：当每轮样本量增加时，在显式异构性阈值条件下慢速类参与度会崩溃。对于PA部署，我们证明了分段包络导数特征，并提供了精确的断点与根候选枚举程序。仿真结果验证了理论发现，表明PASS能够实现更符合条件的参与，从而获得更高的挂钟精度。