LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies

Edge-Cloud hierarchical systems employing intelligence through Deep Neural Networks (DNNs) endure the dilemma of workload distribution within them. Previous solutions proposed to distribute workloads at runtime according to the state of the surroundings, like the wireless conditions. However, such c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 58th ACM/IEEE Design Automation Conference (DAC) S. 403 - 408
Hauptverfasser: Odema, Mohanad, Rashid, Nafiul, Demirel, Berken Utku, Faruque, Mohammad Abdullah Al
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 05.12.2021
Schlagworte:
Deep learning
Design automation
Design methodology
Hierarchical systems
Runtime
Search problems
Wireless communication
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Edge-Cloud hierarchical systems employing intelligence through Deep Neural Networks (DNNs) endure the dilemma of workload distribution within them. Previous solutions proposed to distribute workloads at runtime according to the state of the surroundings, like the wireless conditions. However, such conditions are usually overlooked at design time. This paper addresses this issue for DNN architectural design by presenting a novel methodology, LENS, which administers multi-objective Neural Architecture Search (NAS) for two-tiered systems, where the performance objectives are refashioned to consider the wireless communication parameters. From our experimental search space, we demonstrate that LENS improves upon the traditional solution's Pareto set by 76.47% and 75% with respect to the energy and latency metrics, respectively.
DOI:10.1109/DAC18074.2021.9586259