Along the Time
Authors:
Open Access
- 17 October 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2529-2538
Abstract
Recent years have witnessed remarkable progress on knowledge graph embedding (KGE) methods to learn the representations of entities and relations in static knowledge graphs (SKGs). However, knowledge changes over time. In order to represent the facts happening in a specific time, temporal knowledge graph (TKG) embedding approaches are put forward. While most existing models ignore the independence of semantic and temporal information. We empirically find that current models have difficulty distinguishing representations of the same entity or relation at different timestamps. In this regard, we propose a TimeLine-Traced Knowledge Graph Embedding method (TLT-KGE) for temporal knowledge graph completion. TLT-KGE aims to embed the entities and relations with timestamps as a complex vector or a quaternion vector. Specifically, TLT-KGE models semantic information and temporal information as different axes of complex number space or quaternion space. Meanwhile, two specific components carving the relationship between semantic and temporal information are devised to buoy the modeling. In this way, the proposed method can not only distinguish the independence of the semantic and temporal information, but also establish a connection between them. Experimental results on the link prediction task demonstrate that TLT-KGE achieves substantial improvements over state-of-the-art competitors. The source code will be available on https://github.com/zhangfw123/TLT-KGE.Keywords
Funding Information
- The National Natural Science Foundation of China (U1836206, 61976204, 62176014, U1811461)
- the Project of Youth Innovation Promotion Association CAS, Beijing Nova Program (Z201100006820062)
- the China Postdoctoral Science Foundation (2021M703273)
This publication has 25 references indexed in Scilit:
- Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences2019
- Learning Sequence Encoders for Temporal Knowledge Graph Completion2018
- HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding2018
- A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network2018
- Deriving Validity Time in Knowledge Graph2018
- Word-Entity Duet Representations for Document Ranking2017
- Collaborative Knowledge Base Embedding for Recommender Systems2016
- WikidataCommunications of the ACM, 2014
- Freebase2008
- XI. On quaternions; or on a new system of imaginaries in algebraJournal of Computers in Education, 1848