Reusing Deep Learning Models: Challenges and Directions in Software Engineering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929327526903808 |
|---|---|
| author | Davis, James C. Jajal, Purvish Jiang, Wenxin Schorlemmer, Taylor R. Synovic, Nicholas Thiruvathukal, George K. |
| author_facet | Davis, James C. Jajal, Purvish Jiang, Wenxin Schorlemmer, Taylor R. Synovic, Nicholas Thiruvathukal, George K. |
| contents | Deep neural networks (DNNs) achieve state-of-the-art performance in many areas, including computer vision, system configuration, and question-answering. However, DNNs are expensive to develop, both in intellectual effort (e.g., devising new architectures) and computational costs (e.g., training). Reusing DNNs is a promising direction to amortize costs within a company and across the computing industry. As with any new technology, however, there are many challenges in reusing DNNs. These challenges include both missing technical capabilities and missing engineering practices.
This vision paper describes challenges in current approaches to DNN re-use. We summarize studies of re-use failures across the spectrum of re-use techniques, including conceptual (e.g., reusing based on a research paper), adaptation (e.g., re-using by building on an existing implementation), and deployment (e.g., direct re-use on a new device). We outline possible advances that would improve each kind of re-use. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16688 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reusing Deep Learning Models: Challenges and Directions in Software Engineering Davis, James C. Jajal, Purvish Jiang, Wenxin Schorlemmer, Taylor R. Synovic, Nicholas Thiruvathukal, George K. Software Engineering Deep neural networks (DNNs) achieve state-of-the-art performance in many areas, including computer vision, system configuration, and question-answering. However, DNNs are expensive to develop, both in intellectual effort (e.g., devising new architectures) and computational costs (e.g., training). Reusing DNNs is a promising direction to amortize costs within a company and across the computing industry. As with any new technology, however, there are many challenges in reusing DNNs. These challenges include both missing technical capabilities and missing engineering practices. This vision paper describes challenges in current approaches to DNN re-use. We summarize studies of re-use failures across the spectrum of re-use techniques, including conceptual (e.g., reusing based on a research paper), adaptation (e.g., re-using by building on an existing implementation), and deployment (e.g., direct re-use on a new device). We outline possible advances that would improve each kind of re-use. |
| title | Reusing Deep Learning Models: Challenges and Directions in Software Engineering |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2404.16688 |