# Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them

arXiv: https://arxiv.org/abs/2403.14224 · HTML: https://mlsanity.com/paper/2403.14224/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2024.

## 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)
- [Sharing Knowledge without Sharing Data: Stitches can improve ensembles of disjointly trained models](https://mlsanity.com/paper/2512.17592/) (2025)

## Abstract (arXiv)

Traditional approaches to neuroevolution often start from scratch. This becomes prohibitively expensive in terms of computational and data requirements when targeting modern, deep neural networks. Using a warm start could be highly advantageous, e.g., using previously trained networks, potentially from different sources. This moreover enables leveraging the benefits of transfer learning (in particular vastly reduced training effort). However, recombining trained networks is non-trivial because architectures and feature representations typically differ. Consequently, a straightforward exchange of layers tends to lead to a performance breakdown. We overcome this by matching the layers of parent networks based on their connectivity, identifying potential crossover points. To correct for differing feature representations between these layers we employ stitching, which merges the networks by introducing new layers at crossover points. To train the merged network, only stitching layers need to be considered. New networks can then be created by selecting a subnetwork by choosing which stitching layers to (not) use. Assessing their performance is efficient as only their evaluation on data is required. We experimentally show that our approach enables finding networks that represent novel trade-offs between performance and computational cost, with some even dominating the original networks.