IEEE John Vincent Atanasoff Symposium on Modern Computing
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.
Davis, James C.; Jajal, Purvish; Jiang, Wenxin; Schorlemmer, Taylor R; Synovic, Nicholas; Thiruvathukal, George K., Reusing Deep Learning Models: Challenges and Directions in Software Engineering. IEEE JVA Symposium on Modern Computing at IEEE Services 2023, https://doi.org/10.6084/m9.figshare.23317556.v1
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
© IEEE, 2005.
Available for download on Tuesday, July 01, 2025