Message Passing for Hyper-Relational Knowledge Graphs
This work addresses the challenge of accurately representing complex facts in KGs like Wikidata for improved link prediction, though it is incremental as it builds on existing message passing techniques.
The authors tackled the problem of modeling hyper-relational knowledge graphs (KGs) with additional qualifiers, proposing StarE, a message passing encoder that outperforms existing approaches in link prediction, achieving gains up to 25 MRR points compared to triple-based methods.
Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact. In this work, we propose a message passing based graph encoder - StarE capable of modeling such hyper-relational KGs. Unlike existing approaches, StarE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset - WD50K. Our experiments demonstrate that StarE based LP model outperforms existing approaches across multiple benchmarks. We also confirm that leveraging qualifiers is vital for link prediction with gains up to 25 MRR points compared to triple-based representations.