# Fusion of Graph Neural Networks via Optimal Transport

arXiv: https://arxiv.org/abs/2503.21579 · HTML: https://mlsanity.com/paper/2503.21579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [Model Fusion via Optimal Transport](https://mlsanity.com/paper/1910.05653/) (2019)
- [Optimal Transport for structured data with application on graphs](https://mlsanity.com/paper/1805.09114/) (2018)
- [Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein](https://mlsanity.com/paper/2201.12324/) (2022)
- [Transformer Fusion with Optimal Transport](https://mlsanity.com/paper/2310.05719/) (2023)
- [Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models](https://mlsanity.com/paper/2306.04529/) (2023)
- [On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks](https://mlsanity.com/paper/2110.15538/) (2021)

## Abstract (arXiv)

In this paper, we explore the idea of combining GCNs into one model. To that end, we align the weights of different models layer-wise using optimal transport (OT). We present and evaluate three types of transportation costs and show that the studied fusion method consistently outperforms the performance of vanilla averaging. Finally, we present results suggesting that model fusion using OT is harder in the case of GCNs than MLPs and that incorporating the graph structure into the process does not improve the performance of the method.