Link Prediction with Relational Hypergraphs
This work addresses a challenging problem in graph machine learning for applications involving complex relational data, representing an incremental advancement by extending existing methods to hypergraphs.
The paper tackles link prediction on relational hypergraphs, which is harder than on knowledge graphs, by proposing a framework that applies graph neural networks to fully relational structures. The resulting models achieve state-of-the-art results in inductive and transductive link prediction, substantially outperforming baselines.
Link prediction with knowledge graphs has been thoroughly studied in graph machine learning, leading to a rich landscape of graph neural network architectures with successful applications. Nonetheless, it remains challenging to transfer the success of these architectures to relational hypergraphs, where the task of link prediction is over $k$-ary relations, which is substantially harder than link prediction with knowledge graphs. In this paper, we propose a framework for link prediction with relational hypergraphs, unlocking applications of graph neural networks to fully relational structures. Theoretically, we conduct a thorough analysis of the expressive power of the resulting model architectures via corresponding relational Weisfeiler-Leman algorithms and also via logical expressiveness. Empirically, we validate the power of the proposed model architectures on various relational hypergraph benchmarks. The resulting model architectures substantially outperform every baseline for inductive link prediction, and lead to state-of-the-art results for transductive link prediction.