University of Oulu

Y. Koda et al., "Communication-Efficient Multimodal Split Learning for mmWave Received Power Prediction," in IEEE Communications Letters, vol. 24, no. 6, pp. 1284-1288, June 2020, doi: 10.1109/LCOMM.2020.2978824

Communication-efficient multimodal split learning for mmWave received power prediction

Saved in:
Author: Koda, Yusuke1; Park, Jihong2,3; Bennis, Mehdi4;
Organizations: 1Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan
2University of Oulu
3School of Information Technology, Deakin University, Geelong, VIC 3220, Australia
4Centre for Wireless Communications, University of Oulu, 90014 Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 3 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2020
Publish Date: 2020-08-14


The goal of this study is to improve the accuracy of millimeter wave received power prediction by utilizing camera images and radio frequency (RF) signals, while gathering image inputs in a communication-efficient and privacy-preserving manner. To this end, we propose a distributed multimodal machine learning (ML) framework, coined multimodal split learning (MultSL), in which a large neural network (NN) is split into two wirelessly connected segments. The upper segment combines images and received powers for future received power prediction, whereas the lower segment extracts features from camera images and compresses its output to reduce communication costs and privacy leakage. Experimental evaluation corroborates that MultSL achieves higher accuracy than the baselines utilizing either images or RF signals. Remarkably, without compromising accuracy, compressing the lower segment output by 16× yields 16× lower communication latency and 2.8% less privacy leakage compared to the case without compression.

see all

Series: IEEE communications letters
ISSN: 1089-7798
ISSN-E: 2373-7891
ISSN-L: 1089-7798
Volume: 24
Issue: 6
Pages: 1284 - 1288
DOI: 10.1109/LCOMM.2020.2978824
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Funding: This work was supported in part by JSPS KAKENHI (Grant No. JP17H03266, JP18H01442), and KDDI Foundation. This work was also supported in part by the Academy of Finland under Grant 294128, in part by the 6Genesis Flagship under Grant 318927, in part by the Kvantum Institute Strategic Project (SAFARI), in part by the Academy of Finland through the MISSION Project under Grant 319759, and in part by the NOKIA grant foundation.
Academy of Finland Grant Number: 294128
Detailed Information: 294128 (Academy of Finland Funding decision)
318927 (Academy of Finland Funding decision)
319759 (Academy of Finland Funding decision)
Copyright information: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.