Hyperbolic Hypergraph Neural Networks for Multi-Relational Knowledge Hypergraph Representation

TL;DR

This paper introduces H2GNN, a hyperbolic hypergraph neural network that effectively models multi-relational knowledge hypergraphs by preserving hyperedge information and hierarchies, leading to improved performance in node classification and link prediction.

Contribution

The paper proposes a novel hyper-star message passing scheme within H2GNN that captures hyperedge hierarchies and adjacency in hyperbolic space, addressing information loss in previous methods.

Findings

H2GNN outperforms 15 baselines in node classification.

H2GNN achieves superior results in link prediction.

Hyperbolic space modeling enhances hierarchy capturing.

Abstract

Knowledge hypergraphs generalize knowledge graphs using hyperedges to connect multiple entities and depict complicated relations. Existing methods either transform hyperedges into an easier-to-handle set of binary relations or view hyperedges as isolated and ignore their adjacencies. Both approaches have information loss and may potentially lead to the creation of sub-optimal models. To fix these issues, we propose the Hyperbolic Hypergraph Neural Network (H2GNN), whose essential component is the hyper-star message passing, a novel scheme motivated by a lossless expansion of hyperedges into hierarchies. It implements a direct embedding that consciously incorporates adjacent entities, hyper-relations, and entity position-aware information. As the name suggests, H2GNN operates in the hyperbolic space, which is more adept at capturing the tree-like hierarchy. We compare H2GNN with 15 baselines on knowledge hypergraphs, and it outperforms state-of-the-art approaches in both node classification and link prediction tasks.