Hierarchical and Unsupervised Graph Representation Learning with Loukas’s Coarsening

Hierarchical and Unsupervised Graph Representation Learning with Loukas’s Coarsening

We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: (i) The model is inductive: it can embed new graphs without re-training in the presence of new data; (ii) The method...

Full description

Bibliographic Details
Main Authors: Louis Béthune, Yacouba Kaloga, Pierre Borgnat, Aurélien Garivier, Amaury Habrard
Format: Article
Language:English
Published: MDPI AG 2020-08-01
Series:Algorithms
Subjects:
graph representation learning
Graph2Vec
graph convolutional networks
graph coarsening
unsupervised learning
mutual information maximization
Online Access:https://www.mdpi.com/1999-4893/13/9/206

Internet

https://www.mdpi.com/1999-4893/13/9/206

Similar Items