Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning

arXiv:2405.10621v1 Announce Type: new
Abstract: Temporal Knowledge Graph (TKG) reasoning focuses on predicting events through historical information within snapshots distributed on a timeline. Existing studies mainly concentrate on two perspectives of leveraging the history of TKGs, including capturing evolution of each recent snapshot or correlations among global historical facts. Despite the achieved significant accomplishments, these models still fall short of (1) investigating the influences of multi-granularity interactions across recent snapshots and (2) harnessing the expressive semantics of significant links accorded …

abstract arxiv correlations cs.ai cs.lg distributed event events evolution facts global graph history information knowledge knowledge graph perspectives reasoning studies temporal through timeline type