DGCN: LEARNING GRAPH REPRESENTATIONS VIA DENSE CONNECTIONS A PREPRINT - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2023

DGCN: LEARNING GRAPH REPRESENTATIONS VIA DENSE CONNECTIONS A PREPRINT

Résumé

In the last decades, learning over graph data has become one of the most challenging tasks in deep learning. The generally proposed Graph Neural Network (GNN) framework computes a hidden state for every node in the graph by applying nonlinear transformations to its neighborhood. Then updates the node of interest's hidden state. Nevertheless, the node features can contain discriminative information. That can get lost over GNN layers. Here we present a new variant of GNN architecture where we combine node features and GNN activations to learn nodes representations in the graph. We conduct extensive experiments on two graph prediction tasks (node classification and link prediction) and shows that our method can match and outperforms state-of-the-art results
Fichier principal
Vignette du fichier
abidi et all.pdf (458.9 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03991071 , version 1 (15-02-2023)

Identifiants

  • HAL Id : hal-03991071 , version 1

Citer

Khairi Abidi, Wissem Inoubli, Engelbert Mephu Nguifo. DGCN: LEARNING GRAPH REPRESENTATIONS VIA DENSE CONNECTIONS A PREPRINT. 2023. ⟨hal-03991071⟩
90 Consultations
59 Téléchargements

Partager

More