Communication-Efficient Vertically Split Inference via Over-the-Air Computation

doi:10.1109/SPAWC53906.2023.10304428

	Communication-Efficient Vertically Split Inference via Over-the-Air Computation
	Yang, Peng 1; Wen, Dingzhu2 ; Zeng, Qunsong 3; Wang, Ting 1; Shi, Yuanming2
	2023-09-25
会议录名称	2023 IEEE 24TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC)
ISSN	1948-3244
页码	1-5
发表状态	已发表
DOI	10.1109/SPAWC53906.2023.10304428
摘要	In this paper, a vertically split neural network based edge-device collaborative inference framework is proposed to deal with the issue that heterogeneous raw data samples are obtained by different devices for an inference task as well as to enhance the feature extraction capability of edge devices. To alleviate the communication overhead caused by transmitting the high-dimensional local feature maps, the technique of over-the-air computation (AirComp) is adopted. Furthermore, a broadband channel is considered and orthogonal frequency division multiplexing (OFDM) is leveraged to support the simultaneous aggregation of all dimensions of the local results. Due to the channel fading and noise, a scheme of joint subcarrier allocation, power allocation, and receive beamforming is then proposed to minimize the aggregation distortion and improve the inference accuracy. Extensive experiments are conducted to verify the superiority of the proposed design over benchmarking schemes. © 2023 IEEE.
会议录编者/会议主办者	IEEE Signal Processing Society ; The Institute of Electrical and Electronics Engineers (IEEE)
关键词	split inference over-the-air computation orthogonal frequency division multiplexing
会议名称	24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023
会议地点	Shanghai, China
会议日期	25-28 Sept. 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20234915163077
EI主题词	Orthogonal frequency division multiplexing
EI分类号	711.2 Electromagnetic Waves in Relation to Various Structures
原始文献类型	Conference article (CA)
来源库	IEEE
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348745
专题	信息科学与技术学院信息科学与技术学院_PI研究组_石远明组信息科学与技术学院_PI研究组_文鼎柱组
通讯作者	Yang, Peng
作者单位	1.East China Normal University, Software Engineering Institute, Shanghai; 200062, China 2.ShanghaiTech University, School of Information Science and Technology, Shanghai; 201210, China 3.The University of Hong Kong, Department of Electrical and Electronic Engineering, Hong Kong
推荐引用方式 GB/T 7714	Yang, Peng,Wen, Dingzhu,Zeng, Qunsong,et al. Communication-Efficient Vertically Split Inference via Over-the-Air Computation[C]//IEEE Signal Processing Society, The Institute of Electrical and Electronics Engineers (IEEE):Institute of Electrical and Electronics Engineers Inc.,2023:1-5.