# Reusing Deep Neural Network Models through Model Re-engineering

arXiv: https://arxiv.org/abs/2304.00245 · HTML: https://mlsanity.com/paper/2304.00245/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 60 references that are in the map.
- First posted on arXiv 1 Apr 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [SpotTune: Transfer Learning through Adaptive Fine-tuning](https://mlsanity.com/paper/1811.08737/) (2018)
- [DLFuzz: Differential Fuzzing Testing of Deep Learning Systems](https://mlsanity.com/paper/1808.09413/) (2018)
- [Model-Reuse Attacks on Deep Learning Systems](https://mlsanity.com/paper/1812.00483/) (2018)
- [On the Predictability of Pruning Across Scales](https://mlsanity.com/paper/2006.10621/) (2020)
- [ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection](https://mlsanity.com/paper/2106.08890/) (2021)
- [Teacher Model Fingerprinting Attacks Against Transfer Learning](https://mlsanity.com/paper/2106.12478/) (2021)
- [A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning](https://mlsanity.com/paper/1904.04334/) (2019)
- [Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules](https://mlsanity.com/paper/2110.07720/) (2021)
- [Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models](https://mlsanity.com/paper/2103.04333/) (2021)
- [Patching Weak Convolutional Neural Network Models through Modularization and Composition](https://mlsanity.com/paper/2209.06116/) (2022)

## Built on by (most cited first, 6 of 6)

- [Modularizing while Training: A New Paradigm for Modularizing DNN Models](https://mlsanity.com/paper/2306.09376/) (2023)
- [DNN Modularization via Activation-Driven Training](https://mlsanity.com/paper/2411.01074/) (2024)
- [PeaTMOSS: Mining Pre-Trained Models in Open-Source Software](https://mlsanity.com/paper/2310.03620/) (2023)
- [NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models](https://mlsanity.com/paper/2508.11348/) (2025)
- [Speculative Automated Refactoring of Imperative Deep Learning Programs to Graph Execution](https://mlsanity.com/paper/2504.05424/) (2025)
- [Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models](https://mlsanity.com/paper/2610.05277/) (2026)

## Abstract (arXiv)

Training deep neural network (DNN) models, which has become an important task in today's software development, is often costly in terms of computational resources and time. With the inspiration of software reuse, building DNN models through reusing existing ones has gained increasing attention recently. Prior approaches to DNN model reuse have two main limitations: 1) reusing the entire model, while only a small part of the model's functionalities (labels) are required, would cause much overhead (e.g., computational and time costs for inference), and 2) model reuse would inherit the defects and weaknesses of the reused model, and hence put the new system under threats of security attack. To solve the above problem, we propose SeaM, a tool that re-engineers a trained DNN model to improve its reusability. Specifically, given a target problem and a trained model, SeaM utilizes a gradient-based search method to search for the model's weights that are relevant to the target problem. The re-engineered model that only retains the relevant weights is then reused to solve the target problem. Evaluation results on widely-used models show that the re-engineered models produced by SeaM only contain 10.11% weights of the original models, resulting 42.41% reduction in terms of inference time. For the target problem, the re-engineered models even outperform the original models in classification accuracy by 5.85%. Moreover, reusing the re-engineered models inherits an average of 57% fewer defects than reusing the entire model. We believe our approach to reducing reuse overhead and defect inheritance is one important step forward for practical model reuse.