BiasedWalk: Biased Sampling for Representation Learning on Graphs

Abstract : Network embedding algorithms are able to learn latent feature representations of nodes, transforming networks into lower dimensional vector representations. Typical key applications, which have effectively been addressed using network embeddings, include link prediction, multilabel classification and community detection. In this paper, we propose Biased-Walk, a scalable, unsupervised feature learning algorithm that is based on biased random walks to sample context information about each node in the network. Our random-walk based sampling can behave as Breath-First-Search (BFS) and Depth-First-Search (DFS) samplings with the goal to capture homophily and role equivalence between the nodes in the network. We have performed a detailed experimental evaluation comparing the performance of the proposed algorithm against various baseline methods, on several datasets and learning tasks. The experiment results show that the proposed method outperforms the baseline ones in most of the tasks and datasets.
Type de document :
Communication dans un congrès
International Workshop on High Performance Big Graph Data Management, Analysis, and Mining (BigGraphs), Dec 2018, Seattle, WA, United States
Liste complète des métadonnées

https://hal-centralesupelec.archives-ouvertes.fr/hal-01958902
Contributeur : Fragkiskos Malliaros <>
Soumis le : mardi 18 décembre 2018 - 12:40:01
Dernière modification le : jeudi 7 février 2019 - 15:36:37

Fichier

BiasedWalk.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01958902, version 1

Citation

Duong Nguyen, Fragkiskos Malliaros. BiasedWalk: Biased Sampling for Representation Learning on Graphs. International Workshop on High Performance Big Graph Data Management, Analysis, and Mining (BigGraphs), Dec 2018, Seattle, WA, United States. 〈hal-01958902〉

Partager

Métriques

Consultations de la notice

28

Téléchargements de fichiers

29