TuckER: Tensor Factorization for Knowledge Graph Completion
Abstract
Knowledge graphs are structured representations of real world facts. However, they typically contain only a small subset of all possible facts. Link prediction is the task of inferring missing facts based on existing ones. We propose TuckER, a relatively simple yet powerful linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples. By using this particular decomposition, parameters are shared between relations, enabling multi-task learning. TuckER outperforms previous state-of-the-art models across several standard link prediction datasets.
Cite
Text
Balazevic et al. "TuckER: Tensor Factorization for Knowledge Graph Completion." ICML 2019 Workshops: AMTL, 2019.Markdown
[Balazevic et al. "TuckER: Tensor Factorization for Knowledge Graph Completion." ICML 2019 Workshops: AMTL, 2019.](https://mlanthology.org/icmlw/2019/balazevic2019icmlw-tucker/)BibTeX
@inproceedings{balazevic2019icmlw-tucker,
title = {{TuckER: Tensor Factorization for Knowledge Graph Completion}},
author = {Balazevic, Ivana and Allen, Carl and Hospedales, Timothy},
booktitle = {ICML 2019 Workshops: AMTL},
year = {2019},
url = {https://mlanthology.org/icmlw/2019/balazevic2019icmlw-tucker/}
}