Node Classification Method Based on Hierarchical Hypergraph Neural Network
Feng Xu, Wanyue Xiong, Zizhu Fan, Licheng Sun, Liang-Jian Deng · 2024
Read Node Classification Method Based on Hierarchical Hypergraph Neural Network by Feng Xu, Wanyue Xiong, Zizhu Fan, Licheng Sun, Liang-Jian Deng (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11645074.txt.
Description
Feng Xu and co-authors present a new neural network design for sorting the nodes of a graph into classes. Their 2024 paper builds on hypergraphs, which let one link join many nodes at once instead of just two. Older models of this kind pass notes along the links in a flat way, which can miss far-off links and waste the rich group structure.
Their model, called HCHG, stacks the graph into layers. A standard tool first finds tight groups of nodes, and the model then builds one hypergraph inside each group and a second one that links the groups. Messages move through three routes, so each node learns from both its close neighbors and the wide map. Tests show gains on node sorting tasks and on data built from 3D shapes.
Catalog record
| CREATOR | Feng Xu, Wanyue Xiong, Zizhu Fan, Licheng Sun, Liang-Jian Deng |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |