dc.creator | Almagro Blanco, Pedro | es |
dc.creator | Sancho Caparrini, Fernando | es |
dc.date.accessioned | 2021-04-16T08:58:00Z | |
dc.date.available | 2021-04-16T08:58:00Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Almagro Blanco, P. y Sancho Caparrini, F. (2019). Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling. ArXiv.org, arXiv:1907.08793 | |
dc.identifier.uri | https://hdl.handle.net/11441/107198 | |
dc.description.abstract | 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. | es |
dc.description.sponsorship | Ministerio de Economía, Industria y Competitividad TIN2013-41086-P | es |
dc.description.sponsorship | Ministerio de Economía, Industria y Competitividad FIS2016-76830-C2-2-P | es |
dc.format | application/pdf | es |
dc.format.extent | 14 | es |
dc.language.iso | eng | es |
dc.publisher | Cornell University | es |
dc.relation.ispartof | ArXiv.org, arXiv:1907.08793 | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.title | Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial | es |
dc.relation.projectID | TIN2013-41086-P | es |
dc.relation.projectID | FIS2016-76830-C2-2-P | es |
dc.relation.publisherversion | https://arxiv.org/abs/1907.08793 | es |
dc.journaltitle | ArXiv.org | es |
dc.publication.issue | arXiv:1907.08793 | es |
dc.contributor.funder | Ministerio de Economía, Industria y Competitividad (MINECO). España | es |