.png){kind=icon}
.png){kind=icon}
Return
Augmented graph contrastive learning with view separation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.132156.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a novel graph contrastive learning framework that tackles the challenges of learning on heterophilic graphs. • Our method captures richer similarity-based structures and effectively handles dissimilar patterns in heterophilic graphs. • Extensive experiments validate the superior performance of our method across benchmarks on homophilic and heterophilic graphs.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W