H2GNN combines Lorentz-space centroid aggregation with position-specific relation embeddings in a hyper-star message passing scheme to improve multi-relational knowledge hypergraph representation.
A universal quaternion hypergraph network for multimodal video question answering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Hyperbolic Hypergraph Neural Networks for Multi-Relational Knowledge Hypergraph Representation
H2GNN combines Lorentz-space centroid aggregation with position-specific relation embeddings in a hyper-star message passing scheme to improve multi-relational knowledge hypergraph representation.