.png){kind=icon}
.png){kind=icon}
Return
Structure-augmentation and Attribute-aware Graph Contrastive Learning with Weak Information
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2025.114015.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose the SA-GCL model to address weak information and non-homophilic problems. • SA-GCL fuses four views to tackle non-homophily and enhance node representations. • SA-GCL outperforms baselines on node classification and link prediction across nine datasets.
Keywords:
SA-GCL
non-homophily
node representation
multi-view fusion
graph neural networks