Recommending Pre-Trained Models for IoT Devices
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912170163306496 |
|---|---|
| author | Patil, Parth V. Jiang, Wenxin Peng, Huiyun Lugo, Daniel Kalu, Kelechi G. LeBlanc, Josh Smith, Lawrence Heo, Hyeonwoo Aou, Nathanael Davis, James C. |
| author_facet | Patil, Parth V. Jiang, Wenxin Peng, Huiyun Lugo, Daniel Kalu, Kelechi G. LeBlanc, Josh Smith, Lawrence Heo, Hyeonwoo Aou, Nathanael Davis, James C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18972 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Recommending Pre-Trained Models for IoT Devices Patil, Parth V. Jiang, Wenxin Peng, Huiyun Lugo, Daniel Kalu, Kelechi G. LeBlanc, Josh Smith, Lawrence Heo, Hyeonwoo Aou, Nathanael Davis, James C. Machine Learning Artificial Intelligence Software Engineering 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. |
| title | Recommending Pre-Trained Models for IoT Devices |
| topic | Machine Learning Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2412.18972 |