KBlrn: End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features

Alberto Garcia-Duran, Mathias Niepert
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:371-380, 2018.

Abstract

We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features. KBLRN integrates feature types with a novel combination of neural representation learning and probabilistic product of experts models. To the best of our knowledge, KBLRN is the first approach that learns representations of knowledge bases by integrating latent, relational, and numerical features. We show that instances of KBLRN outperform existing methods on a range of knowledge base completion tasks. We contribute a novel data set enriching commonly used knowledge base completion benchmarks with numerical features. The data sets are available under a permissive BSD-3 license1. We also investigate the impact numerical features have on the KB completion performance of KBLRN.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-garcia-duran18a, title = {KBlrn: End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features}, author = {Garcia-Duran, Alberto and Niepert, Mathias}, booktitle = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {371--380}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/garcia-duran18a/garcia-duran18a.pdf}, url = {https://proceedings.mlr.press/r16/garcia-duran18a.html}, abstract = {We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features. KBLRN integrates feature types with a novel combination of neural representation learning and probabilistic product of experts models. To the best of our knowledge, KBLRN is the first approach that learns representations of knowledge bases by integrating latent, relational, and numerical features. We show that instances of KBLRN outperform existing methods on a range of knowledge base completion tasks. We contribute a novel data set enriching commonly used knowledge base completion benchmarks with numerical features. The data sets are available under a permissive BSD-3 license1. We also investigate the impact numerical features have on the KB completion performance of KBLRN.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T KBlrn: End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features %A Alberto Garcia-Duran %A Mathias Niepert %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-garcia-duran18a %I PMLR %P 371--380 %U https://proceedings.mlr.press/r16/garcia-duran18a.html %V R16 %X We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features. KBLRN integrates feature types with a novel combination of neural representation learning and probabilistic product of experts models. To the best of our knowledge, KBLRN is the first approach that learns representations of knowledge bases by integrating latent, relational, and numerical features. We show that instances of KBLRN outperform existing methods on a range of knowledge base completion tasks. We contribute a novel data set enriching commonly used knowledge base completion benchmarks with numerical features. The data sets are available under a permissive BSD-3 license1. We also investigate the impact numerical features have on the KB completion performance of KBLRN. %Z Reissued by PMLR on 04 October 2026.
APA
Garcia-Duran, A. & Niepert, M.. (2018). KBlrn: End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:371-380 Available from https://proceedings.mlr.press/r16/garcia-duran18a.html. Reissued by PMLR on 04 October 2026.

Related Material