Convolutional Kernel Networks for Graph-Structured Data - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Convolutional Kernel Networks for Graph-Structured Data

Résumé

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
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

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

Identifiants

  • HAL Id : hal-02504965 , version 2

Citer

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⟩
252 Consultations
270 Téléchargements

Partager

Gmail Facebook X LinkedIn More