Graph Neural Network with Curriculum Learning for Imbalanced Node Classification

TL;DR

This paper introduces GNN-CL, a novel framework combining curriculum learning with graph neural networks to effectively address class imbalance in node classification tasks, improving generalization and discrimination.

Contribution

It proposes a new GNN framework with curriculum learning that uses graph-based oversampling and combined loss functions to handle imbalanced node classification.

Findings

Consistently outperforms existing state-of-the-art methods on multiple datasets.

Effectively balances classes and improves node classification accuracy.

Enhances model generalization and discrimination through dynamic training adjustments.

Abstract

Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification. In this work, we reveal the vulnerability of GNN to the imbalance of node labels. Traditional solutions for imbalanced classification (e.g. resampling) are ineffective in node classification without considering the graph structure. Worse still, they may even bring overfitting or underfitting results due to lack of sufficient prior knowledge. To solve these problems, we propose a novel graph neural network framework with curriculum learning (GNN-CL) consisting of two modules. For one thing, we hope to acquire certain reliable interpolation nodes and edges through the novel graph-based oversampling based on smoothness and homophily. For another, we combine graph classification loss and metric learning loss which adjust the distance between different nodes associated with minority class in feature space. Inspired by curriculum learning, we dynamically adjust the weights of different modules during training process to achieve better ability of generalization and discrimination. The proposed framework is evaluated via several widely used graph datasets, showing that our proposed model consistently outperforms the existing state-of-the-art methods.