.png){kind=icon}
.png){kind=icon}
Return
HMTE: Memory-transformer representation learning for knowledge hypergraph completion
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.132560.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose HMTE, a hybrid framework combining memory and Transformer for hypergraphs. • A position-aware self-attention mechanism captures dynamic positional information. • We introduce a selective memory layer for iterative feature updates. • Our model HMTE achieves state-of-the-art performance on knowledge hypergraphs.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W