TY - GEN
T1 - Communication-Efficient Vertically Split Inference via Over-the-Air Computation
AU - Yang, Peng
AU - Wen, Dingzhu
AU - Zeng, Qunsong
AU - Wang, Ting
AU - Shi, Yuanming
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - orthogonal frequency division multiplexing
KW - over-the-air computation
KW - split inference
UR - https://www.scopus.com/pages/publications/85178620678
U2 - 10.1109/SPAWC53906.2023.10304428
DO - 10.1109/SPAWC53906.2023.10304428
M3 - 会议稿件
AN - SCOPUS:85178620678
T3 - IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
SP - 1
EP - 5
BT - 2023 IEEE 24th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023
Y2 - 25 September 2023 through 28 September 2023
ER -