Convolutional Kernel Networks for Graph-Structured Data - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Convolutional Kernel Networks for Graph-Structured Data

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.
Fichier principal
Vignette du fichier
main.pdf (584.71 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02504965 , version 1 (11-03-2020)
hal-02504965 , version 2 (29-06-2020)

Identifiers

  • HAL Id : hal-02504965 , version 2

Cite

Dexiong Chen, Laurent Jacob, Julien Mairal. Convolutional Kernel Networks for Graph-Structured Data. ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienna, Austria. pp.1576-1586. ⟨hal-02504965v2⟩
253 View
273 Download

Share

Gmail Facebook X LinkedIn More