Cluster-guided Contrastive Class-imbalanced Graph Classification

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 C3GNN that integrates the idea of clustering into contrastive learning to enhance class-imbalanced graph classification. Technically, C3GNN 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.

Authors

• Wei Ju College of Computer Science, Sichuan University, Chengdu, China
• Zhengyang Mao School of Computer Science, State Key Laboratory for Multimedia Information Processing, PKU-Anker LLM Lab, Peking University, Beijing, China
• Siyu Yi College of Mathematics, Sichuan University, Chengdu, China
• Yifang Qin School of Computer Science, State Key Laboratory for Multimedia Information Processing, PKU-Anker LLM Lab, Peking University, Beijing, China
• Yiyang Gu School of Computer Science, State Key Laboratory for Multimedia Information Processing, PKU-Anker LLM Lab, Peking University, Beijing, China
• Zhiping Xiao Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA
• Jianhao Shen Huawei Hisilicon, Shanghai, China
• Ziyue Qiao School of Computing and Information Technology, Great Bay University, Dongguan, China
• Ming Zhang

Keywords

No keywords are indexed for this paper.