Abstract
Knowledge Graph (KG) embedding approaches have been proved effective to infer new facts for a KG based on the existing ones–a problem known as KG completion. However, most of them have focused on static KGs, in fact, relational facts in KGs often show temporal dynamics, e.g., the fact (US, has president, Barack Obama, [2009–2017]) is only valid from 2009 to 2017. Therefore, utilizing available time information to develop temporal KG embedding models is an increasingly important problem. In this paper, we propose a new hyperplane-based time-aware KG embedding model for temporal KG completion. By employing the method of time-specific hyperplanes, our model could explicitly incorporate time information in the entity-relation space to predict missing elements in the KG more effectively, especially temporal scopes for facts with missing time information. Moreover, in order to model and infer four important relation patterns including symmetry, antisymmetry, inversion and composition, we map facts happened at the same time into a polar coordinate system. During training procedure, a time-enhanced negative sampling strategy is proposed to get more effective negative samples. Experimental results on datasets extracted from real-world temporal KGs show that our model significantly outperforms existing state-of-the-art approaches for the KG completion task.
Highlights
Introduction rre KnowledgeGraphs (KGs) collect and store human knowledge as large multi-relational directed graphs where nodes represent entities, and typed edges represent relationships between entities
Experimental results on datasets extracted from real-world temporal Knowledge Graph (KG) show that our model significantly outperforms existing state-of-the-art approaches for the KG completion task
In order to get better performance in link prediction and temporal scopes prediction, besides the common entity negative sampling, we explore a time-enhanced negative sampling strategy for time information: Datasets: Our datasets are subsets of two temporal KGs: Integrated Crisis Early Warning System (ICEWS) and YAGO3, which have become standard benchmarks for temporal KG completion
Summary
Notation: Throughout this paper, we present scalars with lower-case letters, vectors with bold lower-case letters and tensors with bold upper-case letters. Relation Patterns: According to the existing literatures [15,16,17,18,19], four types of relation patterns are very important and widely spread in real-world KGs: symmetry, antisymmetry, inversion and composition. Embedding representations and scoring functions of state-of-the-art static and temporal models
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
