Minervini, P;
Costabello, L;
Muñoz, E;
Nováček, V;
Vandenbussche, PY;
(2017)
Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms.
In: Ceci, M and Hollmén, J and Todorovski, L and Vens, C and Džeroski, S, (eds.)
Machine Learning and Knowledge Discovery in Databases.
(pp. pp. 668-683).
Springer Nature: Cham, Switzerland.
Preview |
Text
Minervini_Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms_AAM.pdf - Accepted Version Download (1MB) | Preview |
Abstract
Learning embeddings of entities and relations using neural architectures is an effective method of performing statistical learning on large-scale relational data, such as knowledge graphs. In this paper, we consider the problem of regularizing the training of neural knowledge graph embeddings by leveraging external background knowledge. We propose a principled and scalable method for leveraging equivalence and inversion axioms during the learning process, by imposing a set of model-dependent soft constraints on the predicate embeddings. The method has several advantages: (i) the number of introduced constraints does not depend on the number of entities in the knowledge base; (ii) regularities in the embedding space effectively reflect available background knowledge; (iii) it yields more accurate results in link prediction tasks over non-regularized methods; and (iv) it can be adapted to a variety of models, without affecting their scalability properties. We demonstrate the effectiveness of the proposed method on several large knowledge graphs. Our evaluation shows that it consistently improves the predictive accuracy of several neural knowledge graph embedding models (for instance, the MRR of TransE on WordNet increases by 11%) without compromising their scalability properties.
| Type: | Proceedings paper |
|---|---|
| Title: | Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms |
| Event: | ECML PKDD: Joint European Conference on Machine Learning and Knowledge Discovery in Databases 2017 |
| Location: | Skopje, Macedonia |
| Dates: | 18th-20th September 2017 |
| ISBN-13: | 978-3-319-71248-2 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-319-71249-9_40 |
| Publisher version: | http://doi.org/10.1007/978-3-319-71249-9_40 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | anomaly detection, artificial intelligence, Bayesian networks, classification, clustering algorithms, data mining, data security, data stream, image processing, Kernel method, learning algorithm, machine learning, neural networks, recommender systems, reinforcement learning, signal processing, social networking, supervised learning, Support Vector Machines (SVM), world wide web |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10043029 |
Archive Staff Only
 |
View Item |
