What question did this study set out to answer?

To comprehensively review recent advances, benchmarks, and methodological taxonomies in temporal knowledge graph completion.

August 1, 2023Open Access

Temporal Knowledge Graph Completion: A Survey

View Full Paper

Ask AI

Bookmark

Authors

Survey reviews algorithmic advances in dynamic knowledge graphs, highlighting how modeling temporal validity improves link prediction accuracy.

To comprehensively review recent advances, benchmarks, and methodological taxonomies in temporal knowledge graph completion.
Taxonomized existing completion algorithms according to how they incorporate temporal validity to model dynamic graph evolution.
Summarized fundamental definitions, standard benchmark datasets, and evaluation metrics used across dynamic link prediction.
Explicit integration of temporal validity systematically improves link prediction accuracy compared to static graph models.
Identified existing benchmark limitations and mapped prospective research directions for modeling dynamic multi-relational data.

Cai et al. (2023) studied this question.

View Full Paper

Ask AI

Bookmark

Survey reviews algorithmic advances in dynamic knowledge graphs, highlighting how modeling temporal validity improves link prediction accuracy.