SuperHyperGraph Attention Networks
Year: 2025
Type: article
Abstract: Graph Attention Networks (GAT) employ self-attention to aggregate neighboring node features ingraphs, effectively capturing structural dependencies. HyperGraph Attention Networks (HGAT) extend thismechanism to hypergraphs by alternating attention-based vertex-to-hyperedge and hyperedge-to-vertex up-dates, modeling higher-order relationships. In this work, we introduce the n-SuperHyperGraph Attention Net-work, which leverages SuperHyperGraphs—a hierarchical generalization of hypergraphs—to perform multi-tierattention among supervertices and superedges. Our investigation is purely theoretical; empirical validation viacomputational experiments is left for future study
Author: Fujita1, Takaaki
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7079655831
FWCI:
Cites:
Cited by:
Related to: