Bridging Distinct Spaces in Graph-based Machine Learning - Normandie Université Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Bridging Distinct Spaces in Graph-based Machine Learning

Résumé

Graph-based machine learning, encompassing Graph Edit Distances (GEDs), Graph Kernels, and Graph Neural Networks (GNNs), offers extensive capabilities and exciting potential. While each model possesses unique strengths for graph challenges, interrelations between their underlying spaces remain under-explored. In this paper, we introduce a novel framework for bridging these distinct spaces via GED cost learning. A supervised metric learning approach serves as an instance of this framework, enabling space alignment through pairwise distances and the optimization of edit costs. Experiments reveal the framework’s potential for enhancing varied tasks, including regression, classification, and graph generation, heralding new possibilities in these fields.
Fichier principal
Vignette du fichier
ACPR2023_ged_cost_learn_framework_typo_revised.pdf (768.2 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04194644 , version 1 (03-09-2023)
hal-04194644 , version 2 (05-11-2023)

Identifiants

Citer

Linlin Jia, Xiao Ning, Benoit Gaüzère, Paul Honeine, Kaspar Riesen. Bridging Distinct Spaces in Graph-based Machine Learning. 7th Asian Conference on Pattern Recognition (ACPR2023), Nov 2023, Kitakyushu, Japan. ⟨10.1007/978-3-031-47637-2_1⟩. ⟨hal-04194644v2⟩
39 Consultations
15 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More