Shrinking Embeddings for Hyper-Relational Knowledge Graphs

TL;DR

This paper introduces ShrinkE, a geometric embedding method for hyper-relational knowledge graphs that models complex inference patterns like qualifier monotonicity, implication, and mutual exclusion, improving link prediction accuracy.

Contribution

ShrinkE is the first geometric embedding approach explicitly capturing key inference patterns of hyper-relational facts, enhancing generalization over previous methods.

Findings

Outperforms existing methods on three hyper-relational KG benchmarks.

Effectively models qualifier monotonicity, implication, and mutual exclusion.

Demonstrates superior link prediction accuracy.

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 hyper-relational facts where each fact is composed of a 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 hyper-relational facts such as qualifier monotonicity, qualifier implication, and qualifier mutual exclusion, limiting their generalization capability. To unlock this, we present \emph{ShrinkE}, a geometric hyper-relational KG embedding method aiming to explicitly model these patterns. ShrinkE models the primal triple as a 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.