TNE: A Latent Model for Representation Learning on Networks

Abstract : Network representation learning (NRL) methods aim to map each vertex into a low dimensional space by preserving both local and global structure of a given network. In recent years, various approaches based on random walks have been proposed to learn node embeddings-thanks to their success in several challenging problems. In this paper, we introduce a general framework to enhance node embeddings acquired by means of the random walk-based approaches. Similar to the notion of topical word embeddings in NLP, the proposed framework assigns each vertex to a topic with the favor of various statistical models and community detection methods, and then generates the enhanced community representations. We evaluate our method on two downstream tasks: node classification and link prediction. The experimental results demonstrate that the incorporation of vertex and topic embeddings outperform widely-known baseline NRL methods.
Type de document :
Communication dans un congrès
32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Relational Representation Learning Workshop, Dec 2018, Montréal, Canada
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01957684
Contributeur : Abdulkadir Celikkanat <>
Soumis le : lundi 17 décembre 2018 - 15:01:35
Dernière modification le : jeudi 7 février 2019 - 15:36:29

Fichier

_NeurIPS_2018_Workshop__TNE__A...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01957684, version 1

Citation

Abdulkadir Çelikkanat, Fragkiskos Malliaros. TNE: A Latent Model for Representation Learning on Networks. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Relational Representation Learning Workshop, Dec 2018, Montréal, Canada. 〈hal-01957684〉

Partager

Métriques

Consultations de la notice

44

Téléchargements de fichiers

24