Abstract
Current research on knowledge graphs focuses mostly on static knowledge graphs while ignoring temporal information. Recently, people have begun to study the temporal knowledge graph, which integrates temporal information into KGC, so that the modeling is constantly changing with the knowledge that evolves over time. In this survey, we summarize the existing temporal knowledge graph research, which is divided into extrapolation tasks and interpolation tasks according to time. The extrapolation task is mainly used to predict future facts and consists of three models: Temporal Point Process, Time Series, and other models. The interpolation task extends the existing KGC models to complement the lack of past temporal information, including five models: Translational Distance, Semantic Matching, Neural, Relational Rotation, and Hyperbolic Geometric models.
Sign-in/Register to access full text options 
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.
