Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs significant communication overhead, particularly when a large number of client devices are involved. To address this challenge, we propose an adaptive channel pruning-aided SL (ACP-SL) scheme. In ACP-SL, a label-aware channel importance scoring (LCIS) module is designed to generate channel importance scores, distinguishing important channels from less important ones. Based on these scores, an adaptive channel pruning (ACP) module is developed to prune less important channels, thereby compressing the corresponding smashed data and reducing the communication overhead. Experimental results show that ACP-SL consistently outperforms benchmark schemes in test accuracy. Furthermore, it reaches a target test accuracy in fewer training rounds, thereby reducing communication overhead.

翻译：分割学习（SL）将大部分训练工作负载转移至服务器，从而减轻了客户端设备的计算负担。然而，中间特征表示（称为粉碎数据）的传输会带来显著的通信开销，尤其是在涉及大量客户端设备时。为应对这一挑战，我们提出了一种基于自适应通道剪枝的SL（ACP-SL）方案。在ACP-SL中，设计了一个标签感知通道重要性评分（LCIS）模块，用于生成通道重要性分数，从而区分重要通道与次要通道。基于这些分数，开发了一个自适应通道剪枝（ACP）模块，以剪枝次要通道，从而压缩相应的粉碎数据并降低通信开销。实验结果表明，ACP-SL在测试精度上持续优于基准方案。此外，它能在更少的训练轮次内达到目标测试精度，从而进一步减少通信开销。