Multi-Class Imbalanced Graph Convolutional Network Learning

Networked data often demonstrate the Pareto principle (i. e. , 80/20 rule) with skewed class distributions, where most vertices belong to a few majority classes and minority classes only contain a handful of instances. When presented with imbalanced class distributions, existing graph embedding learning tends to bias to nodes from majority classes, leaving nodes from minority classes under-trained. In this paper, we propose Dual-Regularized Graph Convolutional Networks (DR-GCN) to handle multi-class imbalanced graphs, where two types of regularization are imposed to tackle class imbalanced representation learning. To ensure that all classes are equally represented, we propose a class-conditioned adversarial training process to facilitate the separation of labeled nodes. Meanwhile, to maintain training equilibrium (i. e. , retaining quality of fit across all classes), we force unlabeled nodes to follow a similar latent distribution to the labeled nodes by minimizing their difference in the embedding space. Experiments on real-world imbalanced graphs demonstrate that DR-GCN outperforms the state-of-the-art methods in node classification, graph clustering, and visualization.

Authors

• Min Shi
• Yufei Tang
• Xingquan Zhu Florida Atlantic University
• David Wilson
• Jianxun Liu Hunan University of science and Technology

Keywords

• Data Mining: Classification, Semi-Supervised Learning
• Data Mining: Mining Text, Web, Social Media
• Machine Learning: Deep Learning: Convolutional networks