GOT: An Optimal Transport framework for Graph comparison

GOT: An Optimal Transport framework for Graph comparison

Hermina Petric Maretic, Mireille EL Gheche, Giovanni Chierchia, Pascal Frossard

2 Graph Alignment with Optimal Transport

这篇paper提出基于Optimal Transport的新的distance来比较graph,通过smooth graph signal distributions。我们把这个distance来进行graph alignment,试图找到两个graph的最近的distance。

2.1 Preliminaries

$$W$$ 是adjacency matrix,$$D$$是degree matrix。

Laplacian matrix $$L = D - W$$。

2.2 Smooth graph signals

考虑两个graph $$G_1, G_2$$,对应的Laplacian matrix是$$L_1, L_2$$。

2.3 Wasserstein distance between graphs

2.4 Graph alignmen

3 GOT Algorithm

3.1 Optimization

3.2 Stochastic exploration

results matching ""

    No results matching ""