Learning Representations for Hyper-Relational Knowledge Graphs

TL;DR

This paper introduces a novel framework for learning representations in hyper-relational knowledge graphs by utilizing multiple aggregators to better capture the flow of information between base triples and qualifiers, improving KG completion.

Contribution

It proposes a new multi-aggregator framework that enhances hyper-relational KG representations by considering information flow from both base triples and qualifiers, addressing limitations of previous methods.

Findings

Effective in hyper-relational KG completion tasks

Outperforms existing approaches on multiple datasets

Ablation study confirms component importance

Abstract

Knowledge graphs (KGs) have gained prominence for their ability to learn representations for uni-relational facts. Recently, research has focused on modeling hyper-relational facts, which move beyond the restriction of uni-relational facts and allow us to represent more complex and real-world information. However, existing approaches for learning representations on hyper-relational KGs majorly focus on enhancing the communication from qualifiers to base triples while overlooking the flow of information from base triple to qualifiers. This can lead to suboptimal qualifier representations, especially when a large amount of qualifiers are presented. It motivates us to design a framework that utilizes multiple aggregators to learn representations for hyper-relational facts: one from the perspective of the base triple and the other one from the perspective of the qualifiers. Experiments demonstrate the effectiveness of our framework for hyper-relational knowledge graph completion across multiple datasets. Furthermore, we conduct an ablation study that validates the importance of the various components in our framework. The code to reproduce our results can be found at \url{https://github.com/HarryShomer/QUAD}.