用最优传输对齐图神经网络权重，实现更优融合。
Fusion of Graph Neural Networks via Optimal Transport
- 分层对齐各模型权重，通过最优传输实现融合。
- 融合效果优于简单平均，且在不同成本函数下均稳定提升。
- 图结构信息加入无助于性能提升，说明融合难点在图网络本身。
本文探索将多个图神经网络（GCN）模型融合为单一模型的方法。为此，我们采用最优传输（OT）技术逐层对齐不同模型的权重。提出了三种运输成本函数并进行了评估，结果表明所提出的融合方法始终优于简单的平均策略。最终实验显示，相较于多层感知机（MLP），基于OT的模型融合在图神经网络上更具挑战性；同时，将图结构信息引入对齐过程并未提升融合性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。