Mostra el registre d'ítem simple
Building graph representations of deep vector embeddings
dc.contributor.author | Garcia Gasulla, Dario |
dc.contributor.author | Vilalta Arias, Armand |
dc.contributor.author | Parés Pont, Ferran |
dc.contributor.author | Moreno Vázquez, Jonatan |
dc.contributor.author | Ayguadé Parra, Eduard |
dc.contributor.author | Labarta Mancho, Jesús José |
dc.contributor.author | Cortés García, Claudio Ulises |
dc.contributor.author | Suzumura, Toyotaro |
dc.contributor.other | Universitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.contributor.other | Barcelona Supercomputing Center |
dc.date.accessioned | 2020-07-09T09:20:47Z |
dc.date.available | 2020-07-09T09:20:47Z |
dc.date.issued | 2017 |
dc.identifier.citation | Garcia-Gasulla, D. [et al.]. Building graph representations of deep vector embeddings. A: Workshop on Semantic Deep Learning. "Proceedings of the 2nd Workshop on Semantic Deep Learning (SemDeep-2): September 19, 2017, Montpellier, France". Stroudsburg, PA: Association for Computational Linguistics, 2017, p. 9-15. |
dc.identifier.other | https://arxiv.org/abs/1707.07465 |
dc.identifier.uri | http://hdl.handle.net/2117/192717 |
dc.description.abstract | Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector embedding spaces, which enables the use of traditional machine learning algorithms on top of them. In this short paper we propose the construction of a graph embedding space instead, introducing a methodology to transform the knowledge coded within a deep convolutional network into a topological space (i.e. a network). We outline how such graph can hold data instances, data features, relations between instances and features, and relations among features. Finally, we introduce some preliminary experiments to illustrate how the resultant graph embedding space can be exploited through graph analytics algorithms |
dc.description.sponsorship | This work is partially supported by the Joint Study Agreement no. W156463 under the IBM/BSC Deep Learning Center agreement, by the Spanish Government through Programa Severo Ochoa (SEV-2015- 0493), by the Spanish Ministry of Science and Technology through TIN2015-65316-P project, by the Generalitat de Catalunya (contracts 2014-SGR-1051), and by the Core Research for Evolutional Science and Technology (CREST) program of Japan Science and Technology Agency (JST). |
dc.format.extent | 7 p. |
dc.language.iso | eng |
dc.publisher | Association for Computational Linguistics |
dc.rights | Attribution 4.0 International |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic |
dc.subject.lcsh | Machine learning |
dc.subject.lcsh | Image analysis |
dc.subject.lcsh | Image data mining |
dc.subject.other | Artificial intelligence |
dc.subject.other | Deep learning |
dc.subject.other | Embedding |
dc.subject.other | Complex networks |
dc.subject.other | Graph |
dc.subject.other | Community detection |
dc.subject.other | Transfer learning |
dc.title | Building graph representations of deep vector embeddings |
dc.type | Conference lecture |
dc.subject.lemac | Aprenentatge automàtic |
dc.subject.lemac | Imatges -- Anàlisi |
dc.contributor.group | Universitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic |
dc.contributor.group | Universitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://www.aclweb.org/anthology/W17-7302/ |
dc.rights.access | Open Access |
local.identifier.drac | 28845458 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/AGAUR/V PRI/2014 SGR 1051 |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO//TIN2015-65316-P/ES/COMPUTACION DE ALTAS PRESTACIONES VII/ |
local.citation.author | Garcia-Gasulla, D.; Vilalta, A.; Parés, F.; Moreno, J.; Ayguadé, E.; Labarta, J.; Cortés, U.; Suzumura, T. |
local.citation.contributor | Workshop on Semantic Deep Learning |
local.citation.pubplace | Stroudsburg, PA |
local.citation.publicationName | Proceedings of the 2nd Workshop on Semantic Deep Learning (SemDeep-2): September 19, 2017, Montpellier, France |
local.citation.startingPage | 9 |
local.citation.endingPage | 15 |