https://scholars.lib.ntu.edu.tw/handle/123456789/633754
標題: | C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning | 作者: | Hsieh, Cheng Yen YU-CHUAN CHUANG AN-YEU(ANDY) WU |
關鍵字: | Cloud-edge collaborative learning | communication efficiency | data compression | split learning | 公開日期: | 1-一月-2022 | 卷: | 2022-August | 來源出版物: | IEEE International Workshop on Machine Learning for Signal Processing, MLSP | 摘要: | Most existing studies improve the efficiency of Split learning (SL) by compressing the transmitted features. However, most works focus on dimension-wise compression that transforms high-dimensional features into a low-dimensional space. In this paper, we propose circular convolution-based batch-wise compression for SL (C3-SL) to compress multiple features into one single feature. To avoid information loss while merging multiple features, we exploit the quasi-orthogonality of features in high-dimensional space with circular convolution and superposition. To the best of our knowledge, we are the first to explore the potential of batch-wise compression under the SL scenario. Based on the simulation results on CIFAR-10 and CIFAR-100, our method achieves a 16x compression ratio with negligible accuracy drops compared with the vanilla SL. Moreover, C3-SL significantly reduces 1152x memory and 2.25x computation overhead compared to the state-of-the-art dimension-wise compression method. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/633754 | ISBN: | 9781665485470 | ISSN: | 21610363 | DOI: | 10.1109/MLSP55214.2022.9943507 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。