Shrinking Embeddings for Hyper-Relational Knowledge Graphs
This work addresses the challenge of representing and reasoning with hyper-relational facts in knowledge graphs, which is crucial for AI applications requiring nuanced semantic understanding, though it is incremental as it builds on prior embedding methods.
The paper tackles the problem of link prediction on hyper-relational knowledge graphs, which include qualifiers for more complex semantics, by introducing ShrinkE, a geometric embedding method that explicitly models inference patterns like qualifier monotonicity, implication, and mutual exclusion, achieving superior results on three benchmarks.
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.