Semantic Preserving Embeddings for Multi-Relational Graphs

Autor:	Fernando Sancho Caparrini, Pedro Almagro Blanco
Přispěvatelé:	Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial, Junta de Andalucía, Ministerio de Economía y Competitividad (MINECO). España
Rok vydání:	2017
Předmět:	Semantic Networks Theoretical computer science Artificial neural network Multi-relational Graphs Computer science Neural Autoenconder Feature extraction Link discovery Semantic data model Graph Data modeling Original data
Zdroj:	idUS. Depósito de Investigación de la Universidad de Sevilla instname idUS: Depósito de Investigación de la Universidad de Sevilla Universidad de Sevilla (US)
Popis:	In this paper a new machine learning approach to the study of Multi-Relational Graphs as semantic data structures is presented. It shows how vector representations that maintain semantic and topological features of the original data can be obtained from neural encoding architectures and considering the topological properties of the graph. Also, semantic features of these new representations are tested by using some machine learning tasks and new directions on efficient link discovery methodologies on large relational datasets are investigated. Junta de Andalucía TIC-6064 Ministerio de Economía y Competitividad TIN2013-41086-P
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80fab961deff03b200be572ddb6115b5 Zobrazit plný text záznamu