Reusing Deep Learning Models: Challenges and Directions in Software Engineering-猫眼课题宝

DOI：

10.1109/jva60410.2023.00015

发表时间：

2023-07

期刊：

2023 IEEE John Vincent Atanasoff International Symposium on Modern Computing (JVA)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

James C. Davis;Purvish Jajal;Wenxin Jiang;Taylor R. Schorlemmer;Nicholas Synovic;G. Thiruvathukal

深度神经网络（DNNS）在许多领域（包括计算机视觉，系统配置和提问）中实现最先进的性能。但是，在智力上（例如，设计新的体系结构）和计算成本（例如培训）方面，DNN的开发价格都很高。重复使用DNN是在公司内部和计算行业内摊销成本的有前途的方向。但是，与任何新技术一样，重复使用DNN的挑战很多。这些挑战包括缺少技术能力和缺少工程实践。本愿景论文描述了当前DNN重复使用方法中的挑战。我们总结了对重复使用技术的重复使用失败的研究，包括概念（例如，基于研究论文的重复使用），适应性（例如，通过建立现有实施实施）和部署（例如，在新设备上直接重复使用）。我们概述了可能改善每种重复使用的可能进步。

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). Re-using 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 re-using 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., re-using 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.

Reusing Deep Learning Models: Challenges and Directions in Software Engineering

文献摘要

被引文献

相似文献