Multi-head graph contrastive learning with hop augmentation for node classification

doi:10.1016/j.patcog.2025.112055

Multi-head graph contrastive learning with hop augmentation for node classification

2025-07-04

0

PRE

AI

DOI：10.1016/j.patcog.2025.112055

Original

Original request for help

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.

Multi-head graph contrastive learning with hop augmentation for node classification

Abstract

Journal

Organization