Shrinking embeddings for hyper-relational knowledge graphs

Abstract

Link prediction on knowledge graphs (KGs) has been extensively studied on binary relational KGs, wherein each fact is represented by a triple. A significant amount of important knowledge, however, is represented by hyperrelational facts where each fact is composed ofa primal triple and a set of qualifiers comprising a key-value pair that allows for expressing more complicated semantics. Although some recent works have proposed to embed hyper-relational KGs, these methods fail to capture essential inference patterns of hyperrelational facts such as qualifier monotonicity, qualifier implication, and qualifier mutual exclusion, limiting their generalization capability. To unlock this, we present ShrinkE, a geometric hyper-relational KG embedding method aiming to explicitly model these patterns. ShrinkE models the primal triple asa spatial-functional transformation from the head into a relation-specific box. Each qualifier “shrinks” the box to narrow down the possible answer set and, thus, realizes qualifier monotonicity. The spatial relationships between the qualifier boxes allow for modeling core inference patterns of qualifiers such as implication and mutual exclusion. Experimental results demonstrate ShrinkE’s superiority on three benchmarks of hyper-relational KGs.

More information

Identifiers

ORCID for Steffen Staab: orcid.org/0000-0002-0780-4154

Catalogue record

Export record