Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network

2026-02-03

AI Summary

This work addresses the challenge of label imbalance in graph-structured data, where graph neural networks (GNNs) often underperform on minority-class nodes. To mitigate this issue, the authors propose CL3AN-GNN, a novel model that introduces curriculum learning into GNNs for the first time. The approach employs a three-stage attention architecture—Engage, Enact, and Embed—to progressively learn node representations from simple to complex patterns, thereby alleviating label skew. CL3AN-GNN integrates graph convolutional networks (GCNs), graph attention networks (GATs), multi-hop neighborhood modeling, and dynamic attention weighting, complemented by a curriculum-aligned loss weighting strategy. Evaluated on eight Open Graph Benchmark datasets, the model significantly outperforms existing methods in accuracy, F1 score, and AUC, while also demonstrating faster convergence and stronger generalization capabilities.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Imbalanced node classification in graph neural networks (GNNs) happens when some labels are much more common than others, which causes the model to learn unfairly and perform badly on the less common classes. To solve this problem, we propose a Curriculum-Guided Feature Learning and Three-Stage Attention Network (CL3AN-GNN), a learning network that uses a three-step attention system (Engage, Enact, Embed) similar to how humans learn. The model begins by engaging with structurally simpler features, defined as (1) local neighbourhood patterns (1-hop), (2) low-degree node attributes, and (3) class-separable node pairs identified via initial graph convolutional networks and graph attention networks (GCN and GAT) embeddings. This foundation enables stable early learning despite label skew. The Enact stage then addresses complicated aspects: (1) connections that require multiple steps, (2) edges that connect different types of nodes, and (3) nodes at the edges of minority classes by using adjustable attention weights. Finally, Embed consolidates these features via iterative message passing and curriculum-aligned loss weighting. We evaluate CL3AN-GNN on eight Open Graph Benchmark datasets spanning social, biological, and citation networks. Experiments show consistent improvements across all datasets in accuracy, F1-score, and AUC over recent state-of-the-art methods. The model's step-by-step method works well with different types of graph datasets, showing quicker results than training everything at once, better performance on new, imbalanced graphs, and clear explanations of each step using gradient stability and attention correlation learning curves. This work provides both a theoretically grounded framework for curriculum learning in GNNs and practical evidence of its effectiveness against imbalances, validated through metrics, convergence speeds, and generalisation tests.

Problem

• imbalanced node classification
• graph neural networks
• class imbalance
• minority classes
• label skew

Innovation

• Imbalanced Node Classification
• Curriculum Learning
• Three-Stage Attention
• Graph Neural Networks
• Attention Mechanism