Multi-granularity Adaptive Hypergraph Representation Learning via Granular-ball
A novel framework called Adaptive Granular Hypergraph Generation (MGHRL) is introduced, which generates hyperedges at multiple levels of granularity through the adaptive splitting of granular-ball, effectively capturing high-order relationships based on the graph's topological structure.
Sen Zhao, Yi-Fan Guan, Jin-Yuan Ni et al.
· 0 citations