.png){kind=icon}
.png){kind=icon}
Return
Preference modeling with multi-graph graph attention network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.131872.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposes MG-GAT, a novel multi-graph graph attention network that integrates diverse user and item networks for enhanced preference learning. • Introduces a two-level attention mechanism to dynamically weigh intra- and inter-graph contributions, improving both rating and ranking accuracy. • Demonstrates strong performance across three real-world datasets, including significant gains in cold-start scenarios with limited interaction data.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W