Rel-HNN models each tuple as a hyperedge over attribute-value nodes and reports large accuracy gains, but its hypergraph construction appears to include the target label as an input node.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databases
Rel-HNN models each tuple as a hyperedge over attribute-value nodes and reports large accuracy gains, but its hypergraph construction appears to include the target label as an input node.