Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks

Claudio Bellei
  • Fonction : Auteur
  • PersonId : 1227519
Hussain Alattas
  • Fonction : Auteur

Résumé

We show that a modification of the first layer of a Graph Convolutional Network (GCN) can be used to effectively propagate label information across neighbor nodes, for binary and multi-class classification problems. This is done by selectively eliminating self-loops for the label features during the training phase of a GCN. The GCN architecture is otherwise unchanged, without any extra hyper-parameters, and can be used in both a transductive and inductive setting. We show through several experiments that, depending on how many labels are available during the inference phase, this strategy can lead to a substantial improvement in the model performance compared to a standard GCN approach, including with imbalanced datasets.
Fichier principal
Vignette du fichier
2104.02153.pdf (528.41 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03991083 , version 1 (18-06-2024)

Identifiants

Citer

Claudio Bellei, Hussain Alattas, Nesrine Kaaniche. Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks. 2024. ⟨hal-03991083⟩
0 Consultations
2 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More