Saved in:
Bibliographic Details
Main Authors: Ormaniec, Weronika, Vollenweider, Michael, Hoskovec, Elisa
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.21579
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910896718086144
author Ormaniec, Weronika
Vollenweider, Michael
Hoskovec, Elisa
author_facet Ormaniec, Weronika
Vollenweider, Michael
Hoskovec, Elisa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21579
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fusion of Graph Neural Networks via Optimal Transport
Ormaniec, Weronika
Vollenweider, Michael
Hoskovec, Elisa
Machine Learning
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.
title Fusion of Graph Neural Networks via Optimal Transport
topic Machine Learning
url https://arxiv.org/abs/2503.21579