SpaceRL — A reinforcement learning-based knowledge graph driver

Knowledge Graphs are powerful data structures used by large IT companies and the scientific community alike. They aid in the representation of related information by means of nodes connected through links indicating types of relations. These graphs are used as the basis for several smart application...

ver descrição completa

Detalhes bibliográficos
Autores: Bermudo Bayo, Miguel, Ayala Hernández, Daniel, Hernández Salmerón, Inmaculada Concepción, Ruiz Cortés, David, Toro Bonilla, Miguel
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Recursos:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/171218
Acesso em linha:https://hdl.handle.net/11441/171218
https://doi.org/10.1016/j.softx.2025.102078
Access Level:acceso abierto
Palavra-chave:Knowledge graphs
Reinforcement learning
Explainability
Link prediction
Open source
id ES_dbd434fb2a49ebcccb24c9df48bfecdc
oai_identifier_str oai:idus.us.es:11441/171218
network_acronym_str ES
network_name_str España
repository_id_str
spelling SpaceRL — A reinforcement learning-based knowledge graph driverBermudo Bayo, MiguelAyala Hernández, DanielHernández Salmerón, Inmaculada ConcepciónRuiz Cortés, DavidToro Bonilla, MiguelKnowledge graphsReinforcement learningExplainabilityLink predictionOpen sourceKnowledge Graphs are powerful data structures used by large IT companies and the scientific community alike. They aid in the representation of related information by means of nodes connected through links indicating types of relations. These graphs are used as the basis for several smart applications, such as question answering or product recommendation. However, they are built in an automated unsupervised way, which leads to gaps in information, usually in the form of missing links between related entities in the original data source, which have to be added later by completion techniques. SpaceRL is an end-to-end Python framework designed for the generation of reinforcement learning (RL) agents, which can be used to complete knowledge graphs through link discovery. The purpose of the generated agents is to help identify missing links in a knowledge graph by finding paths that implicitly connect two nodes, incidentally providing a reasoned explanation for the inferred new link. The generation of such agents is a complex task, even more so for a non-expert user. SpaceRL is meant to overcome these limitations by providing a flexible set of tools designed with a wide variety of customization options, in order to adapt to different users’ needs, while also including a variety of state-of-the-art RL algorithms and several embedding models that can be combined to optimize the agents performance. Furthermore, SpaceRL offers different interfaces to make it available either locally (programmatically or via a GUI), or through an OpenAPI-compliant REST API.ElsevierCiencias de la Computación e Inteligencia ArtificialLenguajes y Sistemas InformáticosSpanish Ministry of Science, Innovation and Universities2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/171218https://doi.org/10.1016/j.softx.2025.102078reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésSoftwareX, 30, 102078.PID2019-105471RB-I00https://softxjournal.com/retrieve/pii/S2352711025000457info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1712182026-06-17T12:51:07Z
dc.title.none.fl_str_mv SpaceRL — A reinforcement learning-based knowledge graph driver
title SpaceRL — A reinforcement learning-based knowledge graph driver
spellingShingle SpaceRL — A reinforcement learning-based knowledge graph driver
Bermudo Bayo, Miguel
Knowledge graphs
Reinforcement learning
Explainability
Link prediction
Open source
title_short SpaceRL — A reinforcement learning-based knowledge graph driver
title_full SpaceRL — A reinforcement learning-based knowledge graph driver
title_fullStr SpaceRL — A reinforcement learning-based knowledge graph driver
title_full_unstemmed SpaceRL — A reinforcement learning-based knowledge graph driver
title_sort SpaceRL — A reinforcement learning-based knowledge graph driver
dc.creator.none.fl_str_mv Bermudo Bayo, Miguel
Ayala Hernández, Daniel
Hernández Salmerón, Inmaculada Concepción
Ruiz Cortés, David
Toro Bonilla, Miguel
author Bermudo Bayo, Miguel
author_facet Bermudo Bayo, Miguel
Ayala Hernández, Daniel
Hernández Salmerón, Inmaculada Concepción
Ruiz Cortés, David
Toro Bonilla, Miguel
author_role author
author2 Ayala Hernández, Daniel
Hernández Salmerón, Inmaculada Concepción
Ruiz Cortés, David
Toro Bonilla, Miguel
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Ciencias de la Computación e Inteligencia Artificial
Lenguajes y Sistemas Informáticos
Spanish Ministry of Science, Innovation and Universities
dc.subject.none.fl_str_mv Knowledge graphs
Reinforcement learning
Explainability
Link prediction
Open source
topic Knowledge graphs
Reinforcement learning
Explainability
Link prediction
Open source
description Knowledge Graphs are powerful data structures used by large IT companies and the scientific community alike. They aid in the representation of related information by means of nodes connected through links indicating types of relations. These graphs are used as the basis for several smart applications, such as question answering or product recommendation. However, they are built in an automated unsupervised way, which leads to gaps in information, usually in the form of missing links between related entities in the original data source, which have to be added later by completion techniques. SpaceRL is an end-to-end Python framework designed for the generation of reinforcement learning (RL) agents, which can be used to complete knowledge graphs through link discovery. The purpose of the generated agents is to help identify missing links in a knowledge graph by finding paths that implicitly connect two nodes, incidentally providing a reasoned explanation for the inferred new link. The generation of such agents is a complex task, even more so for a non-expert user. SpaceRL is meant to overcome these limitations by providing a flexible set of tools designed with a wide variety of customization options, in order to adapt to different users’ needs, while also including a variety of state-of-the-art RL algorithms and several embedding models that can be combined to optimize the agents performance. Furthermore, SpaceRL offers different interfaces to make it available either locally (programmatically or via a GUI), or through an OpenAPI-compliant REST API.
publishDate 2025
dc.date.none.fl_str_mv 2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/171218
https://doi.org/10.1016/j.softx.2025.102078
url https://hdl.handle.net/11441/171218
https://doi.org/10.1016/j.softx.2025.102078
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv SoftwareX, 30, 102078.
PID2019-105471RB-I00
https://softxjournal.com/retrieve/pii/S2352711025000457
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869421712073818112
score 15,81155

Registos relacionados