SplitFed Learning (SFL) combines federated learning and split learning to enable collaborative training across distributed edge devices; however, it faces significant challenges in heterogeneous environments with diverse computational and communication capabilities. This paper proposes \textit{SuperSFL}, a federated split learning framework that leverages a weight-sharing super-network to dynamically generate resource-aware client-specific subnetworks, effectively mitigating device heterogeneity. SuperSFL introduces Three-Phase Gradient Fusion (TPGF), an optimization mechanism that coordinates local updates, server-side computation, and gradient fusion to accelerate convergence. In addition, a fault-tolerant client-side classifier and collaborative client--server aggregation enable uninterrupted training under intermittent communication failures. Experimental results on CIFAR-10 and CIFAR-100 with up to 100 heterogeneous clients show that SuperSFL converges $2$--$5\times$ faster in terms of communication rounds than baseline SFL while achieving higher accuracy, resulting in up to $20\times$ lower total communication cost and $13\times$ shorter training time. SuperSFL also demonstrates improved energy efficiency compared to baseline methods, making it a practical solution for federated learning in heterogeneous edge environments.

翻译：分割联邦学习（SFL）结合了联邦学习与分割学习，使得分布式边缘设备能够进行协同训练；然而，在计算与通信能力各异的异构环境中，它面临着重大挑战。本文提出 \textit{SuperSFL}，一种利用权重共享超网络动态生成资源感知的客户端特定子网络的联邦分割学习框架，有效缓解了设备异构性。SuperSFL 引入了三阶段梯度融合（TPGF），这是一种协调本地更新、服务器端计算与梯度融合以加速收敛的优化机制。此外，一个容错的客户端分类器以及客户端-服务器协同聚合机制，使得训练在间歇性通信故障下仍能持续进行。在 CIFAR-10 和 CIFAR-100 数据集上、多达 100 个异构客户端的实验结果表明，与基线 SFL 相比，SuperSFL 在通信轮数上收敛速度快 $2$--$5$ 倍，同时达到更高的精度，使得总通信成本降低高达 $20$ 倍，训练时间缩短高达 $13$ 倍。与基线方法相比，SuperSFL 还展现出更高的能效，使其成为异构边缘环境中联邦学习的一个实用解决方案。