Communication Dans Un Congrès Année : 2022

A Simple Way to Learn Metrics Between Attributed Graphs

Résumé

The choice of good distances and similarity measures between objects is important for many machine learning methods. Therefore, many metric learning algorithms have been developed in recent years, mainly for Euclidean data, in order to improve performance of classification or clustering methods. However, due to difficulties in establishing computable, efficient and differentiable distances between attributed graphs, few metric learning algorithms adapted to graphs have been developed despite the strong interest of the community. In this paper, we address this issue by proposing a new Simple Graph Metric Learning-SGML-model with few trainable parameters based on Simple Graph Convolutional Neural Networks-SGCN-and elements of Optimal Transport theory. This model allows us to build an appropriate distance from a database of labeled (attributed) graphs to improve the performance of simple classification algorithms such as k-NN. This distance can be quickly trained while maintaining good performance as illustrated by the experimental studies presented in this paper.

Fichier principal
Vignette du fichier
kaloga22a.pdf (780.79 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04227049 , version 1 (03-10-2023)

Licence

Identifiants

Citer

Yacouba Kaloga, Pierre. Borgnat, Amaury Habrard. A Simple Way to Learn Metrics Between Attributed Graphs. Proceedings of the First Learning on Graphs Conference (LoG 2022),, Dec 2022, Virtual Event (Republic of Korea), France. ⟨hal-04227049⟩
100 Consultations
128 Téléchargements

Altmetric

Partager

  • More