Roadmap for edge AI

A Dagstuhl Perspective

authored by

Aaron Yi Ding, Ella Peltonen, Tobias Meuser, Atakan Aral, Christian Becker, Schahram Dustdar, Thomas Hiessl, Dieter Kranzlmüller, Madhusanka Liyanage, Setareh Maghsudi, Nitinder Mohan, Jörg Ott, Jan S. Rellermeyer, Stefan Schulte, Henning Schulzrinne, Gürkan Solmaz, Sasu Tarkoma, Blesson Varghese, Lars Wolf

Abstract

Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI. In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimisation, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The Edge AI community investigates novel ML methods for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The goal is to share an envisioned roadmap that can bring together key actors and enablers to further advance the domain of Edge AI.

Organisation(s)

Dependable and Scalable Software Systems

External Organisation(s)

Delft University of Technology
University of Oulu
Technische Universität Darmstadt
University of Vienna
University of Mannheim
TU Wien (TUW)
Ludwig-Maximilians-Universität München (LMU)
University College Dublin
University of Tübingen
Technical University of Munich (TUM)
Hamburg University of Technology (TUHH)
Columbia University
NEC Corporation
University of Helsinki
University of St. Andrews
Technische Universität Braunschweig

Type

Article

Journal

Computer communication review

Volume

52

Pages

28-33

No. of pages

6

ISSN

0146-4833

Publication date

01.03.2022

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Software, Computer Networks and Communications

Electronic version(s)

http://resolver.tudelft.nl/uuid:b9608511-c9ea-4d78-b828-cd58871bf695 (Access: Open)
https://doi.org/10.1145/3523230.3523235 (Access: Closed)