Cluster-guided Contrastive Class-imbalanced Graph Classification

2024-12-17

AI Summary

To address degraded minority-class recognition performance caused by severe class imbalance in graph classification, this paper proposes a clustering-guided hierarchical supervised contrastive learning framework. The method first integrates graph-level K-means clustering with supervised contrastive learning; second, introduces a subclass balancing mechanism to preserve semantic substructures within majority classes; and third, employs graph-structured Mixup augmentation to enhance generalization for minority classes. By jointly optimizing fine-grained structural modeling and cross-class generalization, the approach achieves significant improvements over state-of-the-art methods across multiple real-world graph benchmark datasets under long-tailed distributions. On average, it improves F1-score and AUC by 3.2% and 4.1%, respectively, effectively mitigating performance degradation in imbalanced settings.

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
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This paper studies the problem of class-imbalanced graph classification, which aims at effectively classifying the graph categories in scenarios with imbalanced class distributions. While graph neural networks (GNNs) have achieved remarkable success, their modeling ability on imbalanced graph-structured data remains suboptimal, which typically leads to predictions biased towards the majority classes. On the other hand, existing class-imbalanced learning methods in vision may overlook the rich graph semantic substructures of the majority classes and excessively emphasize learning from the minority classes. To address these challenges, we propose a simple yet powerful approach called C$^3$GNN that integrates the idea of clustering into contrastive learning to enhance class-imbalanced graph classification. Technically, C$^3$GNN clusters graphs from each majority class into multiple subclasses, with sizes comparable to the minority class, mitigating class imbalance. It also employs the Mixup technique to generate synthetic samples, enriching the semantic diversity of each subclass. Furthermore, supervised contrastive learning is used to hierarchically learn effective graph representations, enabling the model to thoroughly explore semantic substructures in majority classes while avoiding excessive focus on minority classes. Extensive experiments on real-world graph benchmark datasets verify the superior performance of our proposed method against competitive baselines.

Problem

• Imbalanced Data
• Graph Neural Networks
• Classification Bias

Innovation

• C^3GNN
• Class-balancing Strategy
• Contrastive Learning