Complex Embeddings for Simple Link Prediction

Théo Trouillon, Johannes Welbl, Sebastian Riedel, Eric Gaussier, Guillaume Bouchard
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2071-2080, 2016.

Abstract

In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v48-trouillon16, title = {Complex Embeddings for Simple Link Prediction}, author = {Trouillon, Théo and Welbl, Johannes and Riedel, Sebastian and Gaussier, Eric and Bouchard, Guillaume}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {2071--2080}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/trouillon16.pdf}, url = {https://proceedings.mlr.press/v48/trouillon16.html}, abstract = {In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks.} }
Endnote
%0 Conference Paper %T Complex Embeddings for Simple Link Prediction %A Théo Trouillon %A Johannes Welbl %A Sebastian Riedel %A Eric Gaussier %A Guillaume Bouchard %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-trouillon16 %I PMLR %P 2071--2080 %U https://proceedings.mlr.press/v48/trouillon16.html %V 48 %X In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks.
RIS
TY - CPAPER TI - Complex Embeddings for Simple Link Prediction AU - Théo Trouillon AU - Johannes Welbl AU - Sebastian Riedel AU - Eric Gaussier AU - Guillaume Bouchard BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-trouillon16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 2071 EP - 2080 L1 - http://proceedings.mlr.press/v48/trouillon16.pdf UR - https://proceedings.mlr.press/v48/trouillon16.html AB - In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks. ER -
APA
Trouillon, T., Welbl, J., Riedel, S., Gaussier, E. & Bouchard, G.. (2016). Complex Embeddings for Simple Link Prediction. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:2071-2080 Available from https://proceedings.mlr.press/v48/trouillon16.html.

Related Material