Regularized online tensor factorization for sparse knowledge graph embeddings
| dc.contributor.author | Zulaika Zurimendi, Unai | |
| dc.contributor.author | Almeida, Aitor | |
| dc.contributor.author | López de Ipiña González de Artaza, Diego | |
| dc.date.accessioned | 2024-11-07T10:24:50Z | |
| dc.date.available | 2024-11-07T10:24:50Z | |
| dc.date.issued | 2023 | |
| dc.date.updated | 2024-11-07T10:24:50Z | |
| dc.description.abstract | Knowledge Graphs represent real-world facts and are used in several applications; however, they are often incomplete and have many missing facts. Link prediction is the task of completing these missing facts from existing ones. Embedding models based on Tensor Factorization attain state-of-the-art results in link prediction. Nevertheless, the embeddings they produce can not be easily interpreted. Inspired by previous work on word embeddings, we propose inducing sparsity in the bilinear tensor factorization model, RESCAL, to build interpretable Knowledge Graph embeddings. To overcome the difficulties that stochastic gradient descent has when producing sparse solutions, we add l1 regularization to the learning objective by using the generalized Regularized Dual Averaging online optimization algorithm. The proposed method substantially improves the interpretability of the learned embeddings while maintaining competitive performance in the standard metrics. | en |
| dc.description.sponsorship | Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. We gratefully acknowledge the support of the Basque Government’s Department of Education for the predoctoral funding; the Ministry of Economy, Industry and Competitiveness of Spain under Grant No.: RTI2018-101045-A-C22 (FuturAAL), PEACEOFMIND project (ref. PID2019-105470RB-C31) and the INCEPTION(PID2021-128969OB-I00) project. Finally, we would like to thank NVIDIA for providing us with their hardware via the Nvidia GPU Grant and the Basque Government for their Grant on scientific equipment acquisition with No. EC-19. | en |
| dc.identifier.citation | Zulaika, U., Almeida, A., & López-de-Ipiña, D. (2023). Regularized online tensor factorization for sparse knowledge graph embeddings. Neural Computing and Applications, 35(1), 787-797. https://doi.org/10.1007/S00521-022-07796-Z | |
| dc.identifier.doi | 10.1007/S00521-022-07796-Z | |
| dc.identifier.issn | 1433-3058 | |
| dc.identifier.uri | http://hdl.handle.net/20.500.14454/1687 | |
| dc.language.iso | eng | |
| dc.publisher | Springer Science and Business Media Deutschland GmbH | |
| dc.rights | © The Author(s) 2022 | |
| dc.subject.other | Interpretable embeddings | |
| dc.subject.other | Knowledge graph embedding | |
| dc.subject.other | Sparse learning | |
| dc.title | Regularized online tensor factorization for sparse knowledge graph embeddings | en |
| dc.type | journal article | |
| dcterms.accessRights | open access | |
| oaire.citation.endPage | 797 | |
| oaire.citation.issue | 1 | |
| oaire.citation.startPage | 787 | |
| oaire.citation.title | Neural Computing and Applications | |
| oaire.citation.volume | 35 | |
| oaire.licenseCondition | https://creativecommons.org/licenses/by/4.0/ | |
| oaire.version | VoR |
Ficheros en el ítem
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- zulaika_regularized_2023.pdf
- Tamaño:
- 574.21 KB
- Formato:
- Adobe Portable Document Format