Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning
School of Physics and Information Engineering, Fuzhou University（福州市物理与信息工程学院）；Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；School of Electrical Engineering and Telecommunications, University of New South Wales Sydney（新南威尔士大学悉尼分校电子与电信工程学院）；Hong Kong JC STEM Lab of Smart City and the Department of Computer Science, City University of Hong Kong（香港智慧城市JC STEM实验室及城市大学计算机科学系）；Data61, CSIRO, Marsfield, NSW 2122, Australia, and the School of Computing Science and Engineering, and the University of New South Wales, Kennington, NSW 2052, Australia（Data61, CSIRO, 澳大利亚马尔斯菲尔德, 新南威尔士州2122, 和计算科学与工程学院, 新南威尔士大学肯宁顿, 新南威尔士州2052, 澳大利亚）
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.
Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
Institute of Computing Technology, Chinese Academy of Science（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Laboratory（中关村实验室）；Sensetime Research（商汤科技研究院）
An Efficient Privacy-aware Split Learning Framework for Satellite Communications
Nanyang Technological University（南洋理工大学）；Stony Brook University（石溪大学）；University of Electronic Science and Technology of China（电子科技大学）；Nottingham Trent University（诺丁汉特伦特大学）；Shandong University（山东大学）；Intel Deutschland GmbH（英特尔德国有限公司）
