Convolutional Kernel Networks for Graph-Structured Data

TL;DR

This paper presents a novel approach that combines kernel methods and neural networks for graph data, enabling effective, interpretable, and scalable graph classification.

Contribution

It introduces multilayer graph kernels that unify graph convolutional networks and kernel methods, providing both unsupervised and trainable models.

Findings

Achieves competitive results on graph classification benchmarks.

Provides a flexible, interpretable graph data representation.

Enables end-to-end training of graph convolutional networks.

Abstract

We introduce a family of multilayer graph kernels and establish new links between graph convolutional neural networks and kernel methods. Our approach generalizes convolutional kernel networks to graph-structured data, by representing graphs as a sequence of kernel feature maps, where each node carries information about local graph substructures. On the one hand, the kernel point of view offers an unsupervised, expressive, and easy-to-regularize data representation, which is useful when limited samples are available. On the other hand, our model can also be trained end-to-end on large-scale data, leading to new types of graph convolutional neural networks. We show that our method achieves competitive performance on several graph classification benchmarks, while offering simple model interpretation. Our code is freely available at https://github.com/claying/GCKN.