Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding

arXiv:2405.00358v1 Announce Type: cross
Abstract: Distinguished from traditional knowledge graphs (KGs), temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately. However, existing TKG approaches still face two main challenges, i.e., the limited capability to model arbitrary timestamps continuously and the lack of rich inference patterns under temporal constraints. In this paper, we propose an innovative TKGE method (PTBox) via polynomial decomposition-based temporal representation and box embedding-based entity representation to tackle the above-mentioned problems. Specifically, we decompose …

abstract approximation arxiv capability challenges cs.ai cs.lg embedding explore face facts graph graphs however inference information knowledge knowledge graph knowledge graphs modeling polynomial reason temporal type via