Graph Convolution Networks for Unsupervised Learning - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2022

Graph Convolution Networks for Unsupervised Learning

Résumé

In recent years, graph convolution networks (GCN) have been proposed as semi-supervised learning approaches. In this paper, we introduce a new objective function to train a GCN in order to adapt it in unsupervised learning context. More precisely, we propose a loss function composed only of unsupervised terms, the first term is the kernel k-means objective function used to capture the shared features information between nodes, and the second is a regularization term that imposes the smoothness of the predicted clusters of the whole data. Thanks to the proposed objective function, we are able to keep the advantages of the classical semi-supervised GCN, while using it in an unsupervised way. Experiments on benchmark datasets show that our proposed unsupervised GCN achieves superior performance compared to state-of-the-art clustering algorithms.
Fichier principal
Vignette du fichier
529323_1_En_3_Chapter_Author SADASC.pdf (465.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04460546 , version 1 (15-02-2024)

Identifiants

Citer

Maria Al Jreidy, Joseph Constantin, Fadi Dornaika, Denis Hamad. Graph Convolution Networks for Unsupervised Learning. Hamlich, Mohamed; Bellatreche, Ladjel; Siadat, Ali; Ventura, Sebastian. Smart Applications and Data Analysis: 4th International Conference, SADASC 2022, Marrakesh, Morocco, September 22-24, 2022, Proceedings, 1677, Springer International Publishing, pp.24-33, 2022, Communications in Computer and Information Science (CCIS,volume 1677), 978-3-031-20489-0. ⟨10.1007/978-3-031-20490-6_3⟩. ⟨hal-04460546⟩
5 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More