Temporal Knowledge Graph Completion: A Survey

Abstract

Knowledge graph completion (KGC) can predict missing links and is crucial for real-world knowledge graphs, which widely suffer from incompleteness. KGC methods assume a knowledge graph is static, but that may lead to inaccurate prediction results because many facts in the knowledge graphs change over time. Recently, emerging methods have shown improved predictive results by further incorporating the timestamps of facts; namely, temporal knowledge graph completion (TKGC). With this temporal information, TKGC methods can learn the dynamic evolution of the knowledge graph that KGC methods fail to capture. In this paper, for the first time, we summarize the recent advances in TKGC research. First, we detail the background of TKGC, including the problem definition, benchmark datasets, and evaluation metrics. Then, we summarize existing TKGC methods based on how timestamps of facts are used to capture the temporal dynamics. Finally, we conclude the paper and present future research directions of TKGC.

References in corpus (7)

• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• Tensor Decompositions for temporal knowledge base completion
• Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
• Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• TempoQR: Temporal Question Reasoning over Knowledge Graphs
• Tucker decomposition-based Temporal Knowledge Graph Completion

Cited by in corpus (4)

• Efficiently Embedding Dynamic Knowledge Graphs
• KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
• VHAKG: A Multi-modal Knowledge Graph Based on Synchronized Multi-view Videos of Daily Activities
• Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey