Hypergraph neural networks obey a strict expressivity hierarchy indexed by hypertree width, creating a Width Wall that no fixed-depth model, hidden dimension, or training procedure can cross for wider patterns.
equation (11)).The gated density embedding is concatenated with the backbone output: ˆyv = MLPout h(L) v ∥g v ·z v ,(12) whereMLP out :R 2dh →R C is a two-layer classifier
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
Hypergraph neural networks obey a strict expressivity hierarchy indexed by hypertree width, creating a Width Wall that no fixed-depth model, hidden dimension, or training procedure can cross for wider patterns.