A Deep Neural Network Architecture to Estimate Node Assignment Costs for the Graph Edit Distance - Université de Tours Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A Deep Neural Network Architecture to Estimate Node Assignment Costs for the Graph Edit Distance

Xavier Cortés
  • Fonction : Auteur
  • PersonId : 1036742
Francesc Serratosa
  • Fonction : Auteur
  • PersonId : 1036750

Résumé

The problem of finding a distance and a correspondence between a pair of graphs is commonly referred to as the Error-tolerant Graph matching problem. The Graph Edit Distance is one of the most popular approaches to solve this problem. This method needs to define a set of parameters and the cost functions aprioristically. On the other hand, in recent years, Deep Neural Networks have shown very good performance in a wide variety of domains due to their robustness and ability to solve non-linear problems. The aim of this paper is to present a model to compute the assignments costs for the Graph Edit Distance by means of a Deep Neural Network previously trained with a set of pairs of graphs properly matched. We empirically show a major improvement using our method with respect to the state-of-the-art results.
Fichier principal
Vignette du fichier
2018SSPRDeepGraph.pdf (1010.2 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01880066 , version 1 (24-09-2018)

Identifiants

  • HAL Id : hal-01880066 , version 1

Citer

Xavier Cortés, Donatello Conte, Hubert Cardot, Francesc Serratosa. A Deep Neural Network Architecture to Estimate Node Assignment Costs for the Graph Edit Distance. Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), Aug 2018, Beijing, China. pp. 429-438. ⟨hal-01880066⟩
78 Consultations
184 Téléchargements

Partager

Gmail Facebook X LinkedIn More