Entrepôts, Représentation et Ingénierie des Connaissances
Publications du laboratoire

Recherche approfondie

par Année
par Auteur
par Thème
par Type
- Global Vectors for Node Representations doi link

Auteur(s): Brochier R., Guille A., Velcin J.

Conference: World Wide Web Conference (WWW) (San Francisco, US, 2019-05-13)

Texte intégral en Openaccess : arxiv

Ref HAL: hal-02056800_v1
Ref Arxiv: 1902.11004
DOI: 10.1145/3308558.3313595
Ref. & Cit.: NASA ADS
Exporter : BibTex | endNote

Most network embedding algorithms consist in measuring co-occurrences of nodes via random walks then learning the embeddings using Skip-Gram with Negative Sampling. While it has proven to be a relevant choice, there are alternatives, such as GloVe, which has not been investigated yet for network embedding. Even though SGNS better handles non co-occurrence than GloVe, it has a worse time-complexity. In this paper, we propose a matrix factorization approach for network embedding, inspired by GloVe, that better handles non co-occurrence with a competitive time-complexity. We also show how to extend this model to deal with networks where nodes are documents, by simultaneously learning word, node and document representations. Quantitative evaluations show that our model achieves state-of-the-art performance, while not being so sensitive to the choice of hyper-parameters. Qualitatively speaking, we show how our model helps exploring a network of documents by generating complementary network-oriented and content-oriented keywords.