Knowledge Hypergraph Embedding Meets Relational Algebra

TL;DR

This paper introduces ReAlE, a novel embedding model for knowledge hypergraphs that captures relational algebra operations, improving link prediction and reasoning capabilities over existing methods.

Contribution

ReAlE is a simple, expressive embedding model that can represent key relational algebra operations and outperforms state-of-the-art models in hypergraph completion tasks.

Findings

ReAlE is fully expressive for primitive relational algebra operations.

ReAlE outperforms existing models in knowledge hypergraph completion.

ReAlE effectively represents operations like renaming, projection, union, selection, and difference.

Abstract

Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation. Current methods do not capture the procedural rules underlying the relations in the graph. We propose a simple embedding-based model called ReAlE that performs link prediction in knowledge hypergraphs (generalized knowledge graphs) and can represent high-level abstractions in terms of relational algebra operations. We show theoretically that ReAlE is fully expressive and provide proofs and empirical evidence that it can represent a large subset of the primitive relational algebra operations, namely renaming, projection, set union, selection, and set difference. We also verify experimentally that ReAlE outperforms state-of-the-art models in knowledge hypergraph completion, and in representing each of these primitive relational algebra operations. For the latter experiment, we generate a synthetic knowledge hypergraph, for which we design an algorithm based on the Erdos-R'enyi model for generating random graphs.