.png){kind=icon}
.png){kind=icon}
Return
PID-GNN: Probabilistically disentangled Laplacian renormalization for uncertainty-aware social recommendation
.png){kind=icon}
PRE
AI
L
Y
S
X
Y
Y
DOI：10.1016/j.physa.2026.131798.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• PID-GNN infers node receptivity and expressivity via variational Bayesian modeling. • Role-conditioned Laplacian reweighting normalizes receiver and sender degrees. • Ciao and Epinions tests with ablation and four-state analyses support PID-GNN.
Journal
P
IF:
3.1
Papers:
1.3K
Citations:
3.6W
Organization
Cited Papers