.png){kind=icon}
Return
Adaptive inductive knowledge graph reasoning for conditional queries
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.133732.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Generalizes to knowledge graphs with disjoint entity sets for conditional queries. • Adaptive edge competition highlights query-relevant edges and suppresses noise. • Adaptive residual fusion balances new and old information to stabilize propagation. • Parallel dual decoders capture symmetric and antisymmetric patterns via gating. • Employs progressive propagation to strengthen long-range multi-hop reasoning.
Keywords:
conditional queries
knowledge graphs
adaptive edge competition
residual fusion
parallel dual decoders
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available
Cited Papers
No cited papers available