Persistent Identifier
|
doi:10.11588/data/CSXYSS |
Publication Date
|
2019-08-19 |
Title
| KGE Algorithms |
Subtitle
| Knowledge Graph Embeddings with Type Regularizer |
Alternative URL
| https://github.com/bhushank/kge |
Author
| Kotnis, Bhushan (Department of Computational Linguistics, Heidelberg University, Germany (2016-2018), NEC Laboratories Europe GmbH (since 2018)) |
Point of Contact
|
Use email button above to contact.
Kotnis, Bhushan (NEC Laboratories Europe GmbH) |
Description
| An updated method for link prediction that uses a regularization factor that models relation argument types Abstract (Kotnis and Nastase, 2017): Learning relations based on evidence from knowledge repositories relies on processing the available relation instances. Knowledge repositories are not balanced in terms of relations or entities – there are relations with less than 10 but also thousands of instances, and entities involved in less than 10 but also thousands of relations. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form of a regularization factor added to the loss function that takes into account the types (categories) of the entities that appear as arguments to relations in the knowledge base. Tested on Freebase, a frequently used benchmarking dataset for link/path predicting tasks, we note increased performance compared to the baseline model in terms of mean reciprocal rank and hits@N, N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer. |
Subject
| Arts and Humanities; Computer and Information Science |
Keyword
| knowledge graphs
graph embedding
link prediction |
Topic Classification
| knowledge discovery in knowledge graphs |
Related Publication
| Bhushan Kotnis and Vivi Nastase. 2017. Learning Knowledge Graph Embeddings. In Proceedings of K-CAP 2017: Knowledge Capture Conference, Austin, TX, USA, December 4-6, 2017 (K-CAP 2017). doi: 10.1145/3148011.3154466 https://arxiv.org/abs/1706.09278 |
Production Date
| 2017 |
Production Location
| Heidelberg University |
Data Type
| program source code |
Related Material
| FB15K datasets
"This FREEBASE FB15k DATA consists of a collection of triplets (synset, relation_type, triplet) extracted from Freebase (http://www.freebase.com). This data set can be seen as a 3-mode tensor depicting ternary relationships between synsets." (see README, in FB15k)
Link to the FB15K dataset: https://everest.hds.utc.fr/lib/exe/fetch.php?media=en:fb15k.tgz
License: Creative Commons Attribution 2.5 License.
When using this data, one should cite the original paper:
Bordes, A., Usunier, N., García-Durán, A., Weston, J., & Yakhnenko, O. (2013). Translating Embeddings for Modeling Multi-relational Data. In Proceedings of Neural Information Processing Systems (NIPS 26), Lake Taho, NV, USA. Dec. 2013. |
Data Source
| M. Nickel, K. Murphy, V. Tresp, and E. Gabrilovich. 2016. A Review of Relational Machine Learning for Knowledge Graphs. In Proc. IEEE 104, 1 (Jan 2016), 11–33. https://doi.org/10.1109/JPROC.2015.2483592
Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2012. Factorizing YAGO: Scalable Machine Learning for Linked Data. In Proceedings of the 21st International Conference on World Wide Web (WWW'12). ACM, New York, NY,USA, 271–280. https://doi.org/10.1145/2187836.2187874
Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating Embeddings for Modeling Multirelational Data. In Advances in Neural Information Processing Systems 26, C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 2787–2795. https://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf
Maximilian Nickel, Lorenzo Rosasco, and Tomaso Poggio. 2016. Holographic Embeddings of Knowledge Graphs. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI'16). AAAI Press, 1955–1961. https://dl.acm.org/citation.cfm?id=3016100.3016172
Theano (Python library): http://deeplearning.net/software/theano/ |