# Towards Migrating Neural Network Implementations

arXiv: https://arxiv.org/abs/2511.02610 · HTML: https://mlsanity.com/paper/2511.02610/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 50 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions](https://mlsanity.com/paper/1909.00590/) (2019)
- [Recurrent Neural Networks (RNNs): A gentle Introduction and Overview](https://mlsanity.com/paper/1912.05911/) (2019)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms](https://mlsanity.com/paper/1909.06727/) (2019)
- [DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization](https://mlsanity.com/paper/2307.04963/) (2023)
- [Building BESSER: an open-source low-code platform](https://mlsanity.com/paper/2405.13620/) (2024)
- [Ivy: Templated Deep Learning for Inter-Framework Portability](https://mlsanity.com/paper/2102.02886/) (2021)
- [EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy](https://mlsanity.com/paper/2008.04175/) (2020)

## Built on by (most cited first, 1 of 1)

- [On the use of LLMs to generate a dataset of Neural Networks](https://mlsanity.com/paper/2602.04388/) (2026)

## Abstract (arXiv)

The development of smart systems (i.e., systems enhanced with AI components) has thrived thanks to the rapid advancements in neural networks (NNs). A wide range of libraries and frameworks have consequently emerged to support NN design and implementation. The choice depends on factors such as available functionalities, ease of use, documentation and community support. After adopting a given NN framework, organizations might later choose to switch to another if performance declines, requirements evolve, or new features are introduced. Unfortunately, migrating NN implementations across libraries is challenging due to the lack of migration approaches specifically tailored for NNs. This leads to increased time and effort to modernize NNs, as manual updates are necessary to avoid relying on outdated implementations and ensure compatibility with new features. In this paper, we propose an approach to automatically migrate neural network code across deep learning frameworks. Our method makes use of a pivot NN model to create an abstraction of the NN prior to migration. We validate our approach using two popular NN frameworks, namely PyTorch and TensorFlow. We also discuss the challenges of migrating code between the two frameworks and how they were approached in our method. Experimental evaluation on five NNs shows that our approach successfully migrates their code and produces NNs that are functionally equivalent to the originals. Artefacts from our work are available online.