DeepAI AI Chat
Log In Sign Up

Wasserstein Weisfeiler-Lehman Graph Kernels

by   Matteo Togninalli, et al.
ETH Zurich

Graph kernels are an instance of the class of R-Convolution kernels, which measure the similarity of objects by comparing their substructures. Despite their empirical success, most graph kernels use a naive aggregation of the final set of substructures, usually a sum or average, thereby potentially discarding valuable information about the distribution of individual components. Furthermore, only a limited instance of these approaches can be extended to continuously attributed graphs. We propose a novel method that relies on the Wasserstein distance between the node feature vector distributions of two graphs, which allows to find subtler differences in data sets by considering graphs as high-dimensional objects, rather than simple means. We further propose a Weisfeiler-Lehman inspired embedding scheme for graphs with continuous node attributes and weighted edges, enhance it with the computed Wasserstein distance, and thus improve the state-of-the-art prediction performance on several graph classification tasks.


page 1

page 2

page 3

page 4


Wasserstein Embedding for Graph Learning

We present Wasserstein Embedding for Graph Learning (WEGL), a novel and ...

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

We present a framework for embedding graph structured data into a vector...

Bures-Wasserstein Means of Graphs

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

Weisfeiler-Lehman meets Gromov-Wasserstein

The Weisfeiler-Lehman (WL) test is a classical procedure for graph isomo...

Graph Kernels Based on Multi-scale Graph Embeddings

Graph kernels are conventional methods for computing graph similarities....

Neighborhood Preserving Kernels for Attributed Graphs

We describe the design of a reproducing kernel suitable for attributed g...

Wasserstein Graph Distance based on L_1-Approximated Tree Edit Distance between Weisfeiler-Lehman Subtrees

The Weisfeiler-Lehman (WL) test has been widely applied to graph kernels...