CGMAE: Self-supervised Masked Auto-Encoder with Cross-Graph node alignment for node classification

doi:10.1016/j.engappai.2025.112910

CGMAE: Self-supervised Masked Auto-Encoder with Cross-Graph node alignment for node classification

2025-10-24

0

PRE

AI

DOI：10.1016/j.engappai.2025.112910

Original

Original request for help

Save

Abstract

En 中文

• A self-supervised paradigm unifies reconstruction and discriminative learning. • A graph MAE with CGNA bridges the reconstruction-classification gap. • Dual-branch encoders reduce graph structural noise. • Experiments on six datasets show strong node classification results.

CGMAE: Self-supervised Masked Auto-Encoder with Cross-Graph node alignment for node classification

Abstract

Journal

Organization