Invariant embedding for graph classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Invariant embedding for graph classification

Résumé

Learning on graphs requires a graph feature representation able to discriminate among different graphs while being amenable to fast computation. The graph isomorphism problem tells us that no fast representation of graphs is known if we require the representation to be both invariant to nodes permutation and able to discriminate two non-isomorphic graphs. Most graph representations explored so far require to be invariant. We explore new graph representations by relaxing this constraint. We present a generic embedding of graphs relying on spectral graph theory called Invariant Graph Embedding (IGE). We show that for a large family of graphs, our embedding is still invariant. To evaluate the quality and utility of our IGE, we apply them to the graph classification problem and show that IGE reaches the state-of-the-art on benchmark datasets.
Fichier principal
Vignette du fichier
galland2019invariant.pdf (175.28 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02947290 , version 1 (24-09-2020)

Identifiants

  • HAL Id : hal-02947290 , version 1

Citer

Alexis Galland, Marc Lelarge. Invariant embedding for graph classification. ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data, Jun 2019, Long Beach, United States. ⟨hal-02947290⟩
200 Consultations
223 Téléchargements

Partager

Gmail Facebook X LinkedIn More