Recommending Pre-Trained Models for IoT Devices

The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM applicability to resource-constrained IoT hardware. Given the many...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Technologies Results (Online) S. 126 - 130
Hauptverfasser: Patil, Parth V., Jiang, Wenxin, Peng, Huiyun, Lugo, Daniel, Kalu, Kelechi G., LeBlanc, Josh, Smith, Lawrence, Heo, Hyeonwoo, Aou, Nathanael, Davis, James C.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 27.04.2025
Schlagworte:
Hardware
Internet of Things
IoT
Machine learning
Model Recommendation
Object recognition
Pre-Trained Models
Quantization (signal)
Recommender systems
Software engineering
Training
Tuning
ISSN:2832-7632
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM applicability to resource-constrained IoT hardware. Given the many PTM options for any given task, engineers often find it too costly to evaluate each model's suitability. Approaches such as LogME, LEEP, and ModelSpider help streamline model selection by estimating task relevance without exhaustive tuning. However, these methods largely leave hardware constraints as future work-a significant limitation in IoT settings. In this paper, we identify the limitations of current model recommendation approaches regarding hardware constraints and introduce a novel, hardware-aware method for PTM selection. We also propose a research agenda to guide the development of effective, hardware-conscious model recommendation systems for IoT applications.
ISSN:2832-7632
DOI:10.1109/ICSE-NIER66352.2025.00031