# Knowledge Hypergraphs: Prediction Beyond Binary Relations

## TL;DR

This paper introduces new embedding methods, HSimplE and HypE, designed specifically for knowledge hypergraphs with relations involving multiple entities, outperforming existing techniques that convert hypergraphs to binary relations.

## Contribution

The paper presents two novel embedding-based models, HSimplE and HypE, tailored for direct prediction in knowledge hypergraphs, along with new datasets and benchmarks.

## Key findings

- HSimplE and HypE outperform baseline methods in hypergraph prediction tasks.
- Proposed models effectively handle relations involving multiple entities.
- New datasets facilitate hypergraph prediction research.

## Abstract

Knowledge graphs store facts using relations between two entities. In this work, we address the question of link prediction in knowledge hypergraphs where relations are defined on any number of entities. While techniques exist (such as reification) that convert non-binary relations into binary ones, we show that current embedding-based methods for knowledge graph completion do not work well out of the box for knowledge graphs obtained through these techniques. To overcome this, we introduce HSimplE and HypE, two embedding-based methods that work directly with knowledge hypergraphs. In both models, the prediction is a function of the relation embedding, the entity embeddings and their corresponding positions in the relation. We also develop public datasets, benchmarks and baselines for hypergraph prediction and show experimentally that the proposed models are more effective than the baselines.