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.
HNHN: Hypergraph networks with hyperedge neurons
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
Introduces Hypergraph U-Nets with PHPool and PHUnpool operators derived from hierarchical clustering dendrograms for hypergraph reconstruction, classification, and anomaly detection.
HND models hypergraph feature propagation as an anisotropic diffusion process governed by a continuous-time PDE, discretized into stable neural layers with energy dissipation and boundedness guarantees.
HADES adapts knowledge distillation for hypergraph neural networks by using quantified node heterophily as a proxy for teacher reliability, yielding student models that often outperform teachers with up to 12.3x faster inference.
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.
-
Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets
Introduces Hypergraph U-Nets with PHPool and PHUnpool operators derived from hierarchical clustering dendrograms for hypergraph reconstruction, classification, and anomaly detection.
-
Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing
HND models hypergraph feature propagation as an anisotropic diffusion process governed by a continuous-time PDE, discretized into stable neural layers with energy dissipation and boundedness guarantees.
-
Heterophily-Aware Adaptive Knowledge Distillation for Hypergraph Neural Networks
HADES adapts knowledge distillation for hypergraph neural networks by using quantified node heterophily as a proxy for teacher reliability, yielding student models that often outperform teachers with up to 12.3x faster inference.