Compressing and Fine-tuning DNNs for Efficient Inference in Mobile Device-Edge Continuum

Pruning deep neural networks (DNN) is a well-known technique that allows for a sensible reduction in inference cost. However, this may severely degrade the accuracy achieved by the model unless the latter is properly fine-tuned, which may, in turn, result in increased computational cost and latency....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom) S. 305 - 310
Hauptverfasser:	Singh, Gurtaj, Chukhno, Olga, Campolo, Claudia, Molinaro, Antonella, Chiasserini, Carla Fabiana
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 08.07.2024
Schlagworte:	Accuracy Artificial neural networks Computational modeling Costs Edge computing Edge-mobile device continuum Machine learning Machine learning pipeline ML model compression Mobile handsets Pipelines
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!