DeepAI AI Chat
Log In Sign Up

A Regularized Wasserstein Framework for Graph Kernels

by   Asiri Wijesinghe, et al.
Australian National University

We propose a learning framework for graph kernels, which is theoretically grounded on regularizing optimal transport. This framework provides a novel optimal transport distance metric, namely Regularized Wasserstein (RW) discrepancy, which can preserve both features and structure of graphs via Wasserstein distances on features and their local variations, local barycenters and global connectivity. Two strongly convex regularization terms are introduced to improve the learning ability. One is to relax an optimal alignment between graphs to be a cluster-to-cluster mapping between their locally connected vertices, thereby preserving the local clustering structure of graphs. The other is to take into account node degree distributions in order to better preserve the global structure of graphs. We also design an efficient algorithm to enable a fast approximation for solving the optimization problem. Theoretically, our framework is robust and can guarantee the convergence and numerical stability in optimization. We have empirically validated our method using 12 datasets against 16 state-of-the-art baselines. The experimental results show that our method consistently outperforms all state-of-the-art methods on all benchmark databases for both graphs with discrete attributes and graphs with continuous attributes.


page 1

page 2

page 3

page 4


Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching

We propose a scalable Gromov-Wasserstein learning (S-GWL) method and est...

Gromov-Wasserstein Learning for Graph Matching and Node Embedding

A novel Gromov-Wasserstein learning framework is proposed to jointly mat...

Transport based Graph Kernels

Graph kernel is a powerful tool measuring the similarity between graphs....

GOT: An Optimal Transport framework for Graph comparison

We present a novel framework based on optimal transport for the challeng...

Solving graph compression via optimal transport

We propose a new approach to graph compression by appeal to optimal tran...

Sequences of well-distributed vertices on graphs and spectral bounds on optimal transport

Given a graph G=(V,E), suppose we are interested in selecting a sequence...

Gromov-Wasserstein Factorization Models for Graph Clustering

We propose a new nonlinear factorization model for graphs that are with ...