Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
2-2022
Abstract
A key to knowledge graph embedding (KGE) is to choose a proper representation space, e.g., point-wise Euclidean space and complex vector space. In this paper, we propose a unified perspective of embedding and introduce uncertainty into KGE from the view of group theory. Our model can incorporate existing models (i.e., generality), ensure the computation is tractable (i.e., efficiency) and enjoy the expressive power of complex random variables (i.e., expressiveness). The core idea is that we embed entities/relations as elements of a symmetric group, i.e., permutations of a set. Permutations of different sets can reflect different properties of embedding. And the group operation of symmetric groups is easy to compute. In specific, we show that the embedding of many existing models, point vectors, can be seen as elements of a symmetric group. To reflect uncertainty, we first embed entities/relations as permutations of a set of random variables. A permutation can transform a simple random variable into a complex random variable for greater expressiveness, called a normalizing flow. We then define scoring functions by measuring the similarity of two normalizing flows, namely NFE. We construct several instantiating models and prove that they are able to learn logical rules. Experimental results demonstrate the effectiveness of introducing uncertainty and our model.
Keywords
Complex random variables, Embeddings, Euclidean spaces, Graph embeddings, Knowledge graphs, Point wise, Representation space, Space Vector, Symmetric groups, Uncertainty
Discipline
Databases and Information Systems
Research Areas
Data Science and Engineering
Publication
Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, DC, February 7-14
Volume
37
First Page
4756
Last Page
4764
ISBN
9781577358800
Publisher
AAAI Press
City or Country
USA
Citation
XIAO, Changyi; HE, Xiangnan; and CAO, Yixin.
Knowledge graph embedding by normalizing flows. (2022). Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, DC, February 7-14. 37, 4756-4764.
Available at: https://ink.library.smu.edu.sg/sis_research/8299
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.