# Reusing Deep Learning Models: Challenges and Directions in Software Engineering

arXiv: https://arxiv.org/abs/2404.16688 · HTML: https://mlsanity.com/paper/2404.16688/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2024.

## Built on by (most cited first, 10 of 10)

- [What do we know about Hugging Face? A systematic literature review and quantitative validation of qualitative claims](https://mlsanity.com/paper/2406.08205/) (2024)
- [An Empirical Analysis of Machine Learning Model and Dataset Documentation, Supply Chain, and Licensing Challenges on Hugging Face](https://mlsanity.com/paper/2502.04484/) (2025)
- [Improving the Reproducibility of Deep Learning Software: An Initial Investigation through a Case Study Analysis](https://mlsanity.com/paper/2505.03165/) (2025)
- [PickleBall: Secure Deserialization of Pickle-based Machine Learning Models (Extended Report)](https://mlsanity.com/paper/2508.15987/) (2025)
- [A Partial Replication of MaskFormer in TensorFlow on TPUs for the TensorFlow Model Garden](https://mlsanity.com/paper/2404.18801/) (2024)
- [PyMilo: A Python Library for ML I/O](https://mlsanity.com/paper/2501.00528/) (2024)
- [How Do Model Export Formats Impact the Development of ML-Enabled Systems? A Case Study on Model Integration](https://mlsanity.com/paper/2502.00429/) (2025)
- [NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models](https://mlsanity.com/paper/2508.11348/) (2025)
- [SafePickle: Robust and Generic ML Detection of Malicious Pickle-based ML Models](https://mlsanity.com/paper/2602.19818/) (2026)
- [An Empirical Investigation of Pre-Trained Deep Learning Model Reuse in the Scientific Process](https://mlsanity.com/paper/2603.13584/) (2026)

## Abstract (arXiv)

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.