mlsanityData to 14 Oct 2026

Fusion of Graph Neural Networks via Optimal Transport

arXiv 2503.21579 ↗First posted 27 Mar 2025cs.LGcited by 0

Not on the map. Why?

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.

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

11 of 14 references.

References · 11

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  3. 2020Benchmarking Graph Neural Networkscited by 680
  4. 2021Merging Models with Fisher-Weighted Averagingcited by 621
  5. 2022Git Re-Basin: Merging Models modulo Permutation Symmetriescited by 471
  6. 2019Model Fusion via Optimal Transportcited by 219
  7. 2018Optimal Transport for structured data with application on graphscited by 172
  8. 2022Optimal Transport Tools (OTT): A JAX Toolbox for all things Wassersteincited by 101
  9. 2023Transformer Fusion with Optimal Transportcited by 36
  10. 2023Git-Theta: A Git Extension for Collaborative Development of Machine Learning Modelscited by 15
  11. 2021On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networkscited by 9

Built on by

Not cited yet.