View
3
Download
0
Category
Preview:
Citation preview
Call For Paper and DemoWorkshop on Wireless Networking Innovations
for Mobile Edge Learning
Scope and MotivationMachine learning (ML) and AI have flourished as key contributors to many research fields, one of whichbeing wireless networking and MEC. Contrarily, very limited works in the wireless networking realmsaimed to facilitate the operation of ML/AI at the edges. Achieving significant advancements in thisreverse direction is becoming more and more indispensable due to the massive amounts of datagenerated at the edge resulting from the rapid adoption of the Internet of Everything. Forecastsenvision that 90% of such data will be analyzed in a distributed manner on the edge devices. Beingmostly wireless/mobile (e.g., wireless sensors, smartphones, laptops, drones, connected vehicles, XRs),resource-constrained, and highly heterogeneous, implementing one or multiple ML/AI jobs on suchdevices requires fundamental changes in and innovative designs of wireless networking and MECprotocols. Meanwhile, training powerful ML models based on the enormous data generated by thesedevices demands highly efficient task/data/parameter exchanges in harsh mobile environments andvarious network settings, while preserving data privacy. These trends have recently established thenew research direction of Mobile Edge Learning (MEL), which calls for innovations in wirelessnetworking, ranging from transmission technologies, network protocols, to MEL-friendly architectures.The purpose of this workshop is to invite submissions on the latest advancements in wirelessnetworking for MEL, to implement fast and efficient edge learning jobs over networks of resource-constrained and heterogeneous mobile devices. It also invites academic and industrial researchers toidentify and discuss the major challenges and standardization visions to support MEL.
Topics of Interest• Adaptive allocation of distributed learning
tasks in heterogeneous MEL environments• Joint allocation of distributed learning tasks
and wireless resources for MEL• Energy awareness and management for MEL• Mobility awareness/management for MEL• Mitigation of physical networking and
computing uncertainties for MEL• Network formations for multiple MEL jobs• Multi-hop routing and parameter
aggregation for MEL• Multi-hop network formations for highly
complicated MEL models• URLLC for MEL• Theoretical modeling and performance
analysis for networks involved in MEL
• Physical, MAC, scheduling, and network layer protocols for MEL
• 5G/6G/ Wi-Fi/Bluetooth enabled MEL• MEL in ad-hoc, sensor, vehicular, UAV, and
cognitive radio networking environments• Self-organizing MEL networks• Network standardization efforts and/or
requirements for MEL• Network authentication and security
measures for MEL• Network architectures and protocols for
privacy-preserving MEL• Applications of MEL in wireless/mobile
environments• MEL for XR, MEC, IoT, V2X, Robotics• MEL field tests and experimental testbeds
Demo Showcase and CompetitionIn addition to technical paper submissions, the workshop will feature a demo showcase andcompetition session, in which:• Two state-of-the-art labs in the field will be invited MEL to showcase their MEL demos• Other demos and testbeds can participate in an MEL demo competition.Interested labs, and enterprises are invited to send a two-page description and a short video of theirdemo/testbed to abcdefg@higk.com and will be notified on their acceptance to showcase their demoand enter the competition
Workshop Organizers• Sameh Sorour
Queen’s University, Canada• Hatem Abou-Zeid
Ericsson, Canada• Yansha Ding
King’s College London, UK• Jun Zhang
Hong Kong Polytechnic University, Hong Kong
Keynote Speakers• Prof. Deniz Gündüz,
Imperial College London, UK• Julien Forgeat
Ericsson Global A.I. Accelerator
Panelist (Tentative)• Daniel Desjardins
King’s Distributed Systems• Rath Vannithamby
Intel Corporation• Rajesh Mishra
Parallel Wireless Inc.• Peter Kairouz
Google• Shiqiang Wang
IBM T. J. Watson Research Center• Arthur Brisebois
Ericsson Global A.I. Accelerator
Important Dates:• Paper Submission
20 January 2021• Acceptance Notification
20 February 2021• Camera Ready
01 March 2021• Demo Application
20 February 2021• Admission Notification
20 March 2021
Paper Submission All papers for must be submitted via EDAS. Full instructions on how to submit papers are provided on the IEEE ICC2021 website: https://icc2021.ieee-icc.org/
Recommended