A comparative study of similarity-based and GNN-based link prediction approaches - Archive ouverte HAL Accéder directement au contenu
Poster De Conférence Année : 2020

A comparative study of similarity-based and GNN-based link prediction approaches

Sabeur Aridhi
Malika Smaïl-Tabbone

Résumé

The task of inferring the missing links in a graph based on its current structure is referred to as link prediction. Link prediction methods that are based on pairwise node similarity are well-established approaches in the literature. They show good prediction performance in many real-world graphs though they are heuristics and lack of universal applicability. On the other hand, the success of neural networks for classification tasks in various domains leads researchers to study them in graphs. When a neural network can operate directly on the graph, then it is termed as the graph neural network (GNN). GNN is able to learn hidden features from graphs which can be used for link prediction task in graphs. Link predictions based on GNNs have gained much attention of researchers due to their convincing high performance in many real-world graphs. This appraisal paper studies some similarity and GNN-based link prediction approaches in the domain of homogeneous graphs that consists of a single type of (attributed) nodes and single type of pairwise links. We evaluate the studied approaches against several benchmark graphs with different properties from various domains.
GEM2020_paper_5.pdf (612.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03473689 , version 1 (09-12-2021)

Identifiants

  • HAL Id : hal-03473689 , version 1

Citer

Kamrul Islam, Sabeur Aridhi, Malika Smaïl-Tabbone. A comparative study of similarity-based and GNN-based link prediction approaches. GEM (Graph Embedding and Mining) workshop, ECML-PKDD 2020, Sep 2020, Ghent, Belgium. ⟨hal-03473689⟩
15 Consultations
65 Téléchargements

Partager

Gmail Facebook X LinkedIn More