Reusing Deep Learning Models: Challenges and Directions in Software Engineering

TL;DR

This paper discusses the challenges in reusing deep neural networks across different stages, highlighting technical and engineering issues, and proposes directions for future improvements to make re-use more effective.

Contribution

It provides a comprehensive overview of current challenges in DNN re-use and suggests potential advances to address these issues across conceptual, adaptation, and deployment stages.

Findings

Re-use failures occur across all re-use techniques.

Technical and engineering challenges hinder DNN re-use.

Proposed directions aim to improve re-use effectiveness.

Abstract

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.