Adaptive imbalanced node classification graph contrastive learning

doi:10.1016/j.neucom.2025.131280

Adaptive imbalanced node classification graph contrastive learning

2025-08-18

0

PRE

AI

DOI：10.1016/j.neucom.2025.131280

Original

Original request for help

Save

Abstract

En 中文

• We introduce a VGAE with an encoder-decoder structure to learn graph structure and node features, improving robustness and generalization for pseudo-label generation. • We design a graph-tailored resampling strategy. We prioritize removing low-importance nodes during undersampling and synthesizing high-importance nodes during oversampling. • We create a multi-level, step-by-step sampling strategy. A hybrid sampling method adjusts class proportions, and an augmentation function retains minority node information. • We develop a new data augmentation technique that prioritizes keeping minority class node information while masking majority class nodes, helping the model capture minority features.

Keywords:

VGAE

graph resampling

minority class augmentation

pseudo-label generation

node feature learning

Adaptive imbalanced node classification graph contrastive learning

Abstract

Journal

Organization