Imbalanced graph learning via mixed entropy minimization

• Published in: Scientific reports Vol. 14; no. 1; pp. 24892 - 13
• Main Authors: Xu, Liwen, Zhu, Huaguang, Chen, Jiali
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22.10.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1046; 639/705/117; 639/705/531; 639/705/794; Classification; Entropy; Graph learning; Humanities and Social Sciences; Imbalanced node classification; Mixed entropy minimization (ME); multidisciplinary; Science; Science (multidisciplinary); Training; Mixed entropy minimization (ME); Graph learning; Imbalanced node classification
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-75999-6

Imbalanced datasets, where the minority class is underrepresented, pose significant challenges for node classification in graph learning. Traditional methods often address this issue through synthetic oversampling techniques for the minority class, which can complicate the training process. To address these challenges, we introduce a novel training paradigm for node classification on imbalanced graphs, based on mixed entropy minimization ( ME ). Our proposed method, GraphME , offers a ‘free imbalance defense’ against class imbalance without requiring additional steps to improve classification performance. ME aims to achieve the same goal as cross-entropy-maximizing the model’s probability for the correct classes-while effectively reducing the impact of incorrect class probabilities through a “guidance” term that ensures a balanced trade-off. We validate the effectiveness of our approach through experiments on multiple datasets, where GraphME consistently outperforms the traditional cross-entropy objective, demonstrating enhanced robustness. Moreover, our method can be seamlessly integrated with various adversarial training techniques, leading to substantial improvements in robustness. Notably, GraphME enhances classification accuracy without compromising efficiency, a significant improvement over existing methods. The GraphME code is available at: https://github.com/12chen20/GraphME .