On a linear fused Gromov-Wasserstein distance for graph structured data

03/09/2022
by   Dai Hai Nguyen, et al.
4

We present a framework for embedding graph structured data into a vector space, taking into account node features and topology of a graph into the optimal transport (OT) problem. Then we propose a novel distance between two graphs, named linearFGW, defined as the Euclidean distance between their embeddings. The advantages of the proposed distance are twofold: 1) it can take into account node feature and structure of graphs for measuring the similarity between graphs in a kernel-based framework, 2) it can be much faster for computing kernel matrix than pairwise OT-based distances, particularly fused Gromov-Wasserstein, making it possible to deal with large-scale data sets. After discussing theoretical properties of linearFGW, we demonstrate experimental results on classification and clustering tasks, showing the effectiveness of the proposed linearFGW.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2020

Wasserstein Embedding for Graph Learning

We present Wasserstein Embedding for Graph Learning (WEGL), a novel and ...
research
11/07/2018

Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties

Optimal transport theory has recently found many applications in machine...
research
05/31/2022

Template based Graph Neural Network with Optimal Transport Distances

Current Graph Neural Networks (GNN) architectures generally rely on two ...
research
06/04/2019

Wasserstein Weisfeiler-Lehman Graph Kernels

Graph kernels are an instance of the class of R-Convolution kernels, whi...
research
06/07/2020

Generalized Spectral Clustering via Gromov-Wasserstein Learning

We establish a bridge between spectral clustering and Gromov-Wasserstein...
research
02/02/2022

Topological Classification in a Wasserstein Distance Based Vector Space

Classification of large and dense networks based on topology is very dif...
research
05/31/2023

Bures-Wasserstein Means of Graphs

Finding the mean of sampled data is a fundamental task in machine learni...

Please sign up or login with your details

Forgot password? Click here to reset