Cooperative Inference of DNNs over Noisy Wireless Channels

Sangseok Yun, Jae Mo Kang, Sooyong Choi, Il Min Kim

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


This work studies cooperative inference of deep neural networks (DNNs), in which the inference process is performed in a cooperative manner by an edge device and an edge server. In particular, a practical noisy wireless channel between the edge device and the edge server is considered in this work, unlike the previous works which only considered ideal and simplistic error-free communications between them. To prevent the prediction of DNNs from being inaccurate, the communication errors caused by the noisy wireless channel must be appropriately mitigated. Thus, in the proposed cooperative DNN inference, a hybrid automatic repeat request with chase combining (HARQ-CC) is adopted with a practical error correction code (ECC). Analyzing the end-to-end latency of the proposed cooperative DNN inference, we jointly determine the optimal code rate of the ECC and the optimal location at which the DNN must be split into two parts for the edge device and the edge server to minimize the end-to-end latency. The experimental results show that the proposed cooperative DNN inference considerably outperforms other comparable schemes in previous works.

Original languageEnglish
Article number9464679
Pages (from-to)8298-8303
Number of pages6
JournalIEEE Transactions on Vehicular Technology
Issue number8
Publication statusPublished - 2021 Aug

Bibliographical note

Funding Information:
Manuscript received October 28, 2020; revised February 23, 2021; accepted May 27, 2021. Date of publication June 24, 2021; date of current version August 13, 2021. This work was supported by Brain Pool Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (No. NRF-2020H1D3A2A01056665). The review of this article was coordinated by Prof. Shibo He. (Corresponding author: Il-Min Kim.) Sangseok Yun is with the Department of Information and Communications Engineering, Pukyong National University, Busan 48513, South Korea (e-mail:

Publisher Copyright:
© 1967-2012 IEEE.

All Science Journal Classification (ASJC) codes

  • Automotive Engineering
  • Aerospace Engineering
  • Electrical and Electronic Engineering
  • Applied Mathematics


Dive into the research topics of 'Cooperative Inference of DNNs over Noisy Wireless Channels'. Together they form a unique fingerprint.

Cite this