Artículo
Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling
Autor/es | Almagro Blanco, Pedro
Sancho Caparrini, Fernando |
Departamento | Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial |
Fecha de publicación | 2019 |
Fecha de depósito | 2021-04-16 |
Publicado en |
|
Resumen | Network embedding techniques inspired by word2vec represent an e ective unsuper-
vised relational learning model. Commonly, by means of a Skip-Gram procedure, these
techniques learn low dimensional vector representations ... Network embedding techniques inspired by word2vec represent an e ective unsuper- vised relational learning model. Commonly, by means of a Skip-Gram procedure, these techniques learn low dimensional vector representations of the nodes in a graph by sam- pling node-context examples. Although many ways of sampling the context of a node have been proposed, the e ects of the way a node is chosen have not been analyzed in depth. To ll this gap, we have re-implemented the main four word2vec inspired graph embedding techniques under the same framework and analyzed how di erent sampling distributions a ects embeddings performance when tested in node classi cation problems. We present a set of experiments on di erent well known real data sets that show how the use of popular centrality distributions in sampling leads to improvements, obtaining speeds of up to 2 times in learning times and increasing accuracy in all cases. |
Agencias financiadoras | Ministerio de Economía, Industria y Competitividad (MINECO). España |
Identificador del proyecto | TIN2013-41086-P
FIS2016-76830-C2-2-P |
Cita | Almagro Blanco, P. y Sancho Caparrini, F. (2019). Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling. ArXiv.org, arXiv:1907.08793 |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Improving skip-gram based graph ... | 457.9Kb | [PDF] | Ver/ | |