Machine learning (ML) is a promising enabler for the fifth-generation (5G) communication systems and beyond. By imbuing intelligence into the network edge, edge nodes can proactively carry out decision-making and, thereby, react to local environmental changes and disturbances while experiencing zero communication latency. To achieve this goal, it is essential to cater for high ML inference accuracy at scale under the time-varying channel and network dynamics, by continuously exchanging fresh data and ML model updates in a distributed way. Taming this new kind of data traffic boils down to improving the communication efficiency of distributed learning by optimizing communication payload types, transmission techniques, and scheduling, as well as ML architectures, algorithms, and data processing methods. To this end, this article aims to provide a holistic overview of relevant communication and ML principles and, thereby, present communication-efficient and distributed learning frameworks with selected use cases.
|Number of pages||24|
|Journal||Proceedings of the IEEE|
|Publication status||Published - 2021 May|
Bibliographical noteFunding Information:
Manuscript received August 5, 2020; revised December 2, 2020; accepted January 19, 2021. Date of publication February 18, 2021; date of current version April 30, 2021. This work was supported in part by the INFOTECH Project NOOR, in part by the NEGEIN Project, in part by the EU-CHISTERA projects LeadingEdge and CONNECT, in part by the EU-H2020 Project (IntellIoT), in part by the Academy of Finland projects MISSION and SMARTER, and in part by the Institute for Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (MSIT) under Grant 2018-0-00170 (Virtual Presence in Moving Objects Through 5G). (Corresponding author: Jihong Park.) Jihong Park is with the School of Information Technology, Deakin University, Geelong, VIC 3220, Australia (e-mail: email@example.com). Sumudu Samarakoon, Anis Elgabli, and Mehdi Bennis are with the Centre for Wireless Communications, University of Oulu, 90014 Oulu, Finland (e-mail: firstname.lastname@example.org; email@example.com; firstname.lastname@example.org). Joongheon Kim is with the School of Electrical Engineering, Korea University, Seoul 02841, South Korea (e-mail: email@example.com). Seong-Lyun Kim is with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, South Korea (e-mail: firstname.lastname@example.org). Mérouane Debbah is with the CNRS, CentraleSupélec, Université Paris-Saclay, 91190 Gif-sur-Yvette, France, and also with the Lagrange Mathematical and Computing Research Center, 75007 Paris, France (e-mail: email@example.com).
Dr. Kim was a recipient of the Annenberg Graduate Fellowship with his Ph.D. admission from USC in 2009, the Intel Corporation Next Generation and Standards (NGS) Division Recognition Award in 2015, the Haedong Young Scholar Award by the Korea Institute of Communication and Information Sciences (KICS) in 2018, the IEEE Vehicular Technology Society (VTS) Seoul Chapter Award in 2019, the Outstanding Contribution Award by KICS in 2019, the Gold Paper Award from the IEEE Seoul Section Student Paper Contest in 2019, and the IEEE SYSTEMS JOURNAL Best Paper Award in 2020. He also serves as an Associate Editor for IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY.
© 1963-2012 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Science(all)
- Electrical and Electronic Engineering