# StitchNet: Composing Neural Networks from Pre-Trained Fragments

arXiv: https://arxiv.org/abs/2301.01947 · HTML: https://mlsanity.com/paper/2301.01947/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 5 Jan 2023.

## Builds on (most cited first, 18 of 18)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth](https://mlsanity.com/paper/2010.15327/) (2020)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [Convergent Learning: Do different neural networks learn the same representations?](https://mlsanity.com/paper/1511.07543/) (2015)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Similarity and Matching of Neural Network Representations](https://mlsanity.com/paper/2110.14633/) (2021)
- [Deep Model Reassembly](https://mlsanity.com/paper/2210.17409/) (2022)
- [Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation](https://mlsanity.com/paper/1810.11750/) (2018)
- [Co-regularized Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.05443/) (2018)
- [Similarity of Neural Networks with Gradients](https://mlsanity.com/paper/2003.11498/) (2020)
- [Shared Representational Geometry Across Neural Networks](https://mlsanity.com/paper/1811.11684/) (2018)

## Built on by (most cited first, 2 of 2)

- [How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching](https://mlsanity.com/paper/2412.11299/) (2024)
- [A Stitch in Time Saves Nine: Preserving Policy Compatibility Under Perception Updates in End-to-End Autonomous Driving](https://mlsanity.com/paper/2606.21509/) (2026)

## Abstract (arXiv)

We propose StitchNet, a novel neural network creation paradigm that stitches together fragments (one or more consecutive network layers) from multiple pre-trained neural networks. StitchNet allows the creation of high-performing neural networks without the large compute and data requirements needed under traditional model creation processes via backpropagation training. We leverage Centered Kernel Alignment (CKA) as a compatibility measure to efficiently guide the selection of these fragments in composing a network for a given task tailored to specific accuracy needs and computing resource constraints. We then show that these fragments can be stitched together to create neural networks with accuracy comparable to that of traditionally trained networks at a fraction of computing resource and data requirements. Finally, we explore a novel on-the-fly personalized model creation and inference application enabled by this new paradigm. The code is available at https://github.com/steerapi/stitchnet.