.png){kind=icon}
Return
Multi-head graph contrastive learning with hop augmentation for node classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112055.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• HA: Robust feature augmentation preserving structure integrity using multi-hop info. • MHGCL-HA’s 2V variant boosts efficiency and cuts resource use. • Multi-head contrastive loss enriches node embeddings via multi-view contrast.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available
Cited Papers
Hypergraph modeling and hypergraph multi-view attention neural network for link prediction.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveUniG-Encoder: A universal feature encoder for graph and hypergraph node classificationPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveShareSaveShareSaveShareSaveShareSave
View more