Kronecker Decomposition for Knowledge Graph Embeddings

C. Demir, J. Lienen, A.-C. Ngonga Ngomo, ArXiv:2205.06560 (2022).

Preprint | English
Knowledge graph embedding research has mainly focused on learning continuous representations of entities and relations tailored towards the link prediction problem. Recent results indicate an ever increasing predictive ability of current approaches on benchmark datasets. However, this effectiveness often comes with the cost of over-parameterization and increased computationally complexity. The former induces extensive hyperparameter optimization to mitigate malicious overfitting. The latter magnifies the importance of winning the hardware lottery. Here, we investigate a remedy for the first problem. We propose a technique based on Kronecker decomposition to reduce the number of parameters in a knowledge graph embedding model, while retaining its expressiveness. Through Kronecker decomposition, large embedding matrices are split into smaller embedding matrices during the training process. Hence, embeddings of knowledge graphs are not plainly retrieved but reconstructed on the fly. The decomposition ensures that elementwise interactions between three embedding vectors are extended with interactions within each embedding vector. This implicitly reduces redundancy in embedding vectors and encourages feature reuse. To quantify the impact of applying Kronecker decomposition on embedding matrices, we conduct a series of experiments on benchmark datasets. Our experiments suggest that applying Kronecker decomposition on embedding matrices leads to an improved parameter efficiency on all benchmark datasets. Moreover, empirical evidence suggests that reconstructed embeddings entail robustness against noise in the input knowledge graph. To foster reproducible research, we provide an open-source implementation of our approach, including training and evaluation scripts as well as pre-trained models in our knowledge graph embedding framework.
Publishing Year
Journal Title

Cite this

Demir C, Lienen J, Ngonga Ngomo A-C. Kronecker Decomposition for Knowledge Graph Embeddings. arXiv:220506560. Published online 2022.
Demir, C., Lienen, J., & Ngonga Ngomo, A.-C. (2022). Kronecker Decomposition for Knowledge Graph Embeddings. In arXiv:2205.06560.
@article{Demir_Lienen_Ngonga Ngomo_2022, title={Kronecker Decomposition for Knowledge Graph Embeddings}, journal={arXiv:2205.06560}, author={Demir, Caglar and Lienen, Julian and Ngonga Ngomo, Axel-Cyrille}, year={2022} }
Demir, Caglar, Julian Lienen, and Axel-Cyrille Ngonga Ngomo. “Kronecker Decomposition for Knowledge Graph Embeddings.” ArXiv:2205.06560, 2022.
C. Demir, J. Lienen, and A.-C. Ngonga Ngomo, “Kronecker Decomposition for Knowledge Graph Embeddings,” arXiv:2205.06560. 2022.
Demir, Caglar, et al. “Kronecker Decomposition for Knowledge Graph Embeddings.” ArXiv:2205.06560, 2022.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access


Marked Publications

Open Data LibreCat

Search this title in

Google Scholar