---
title: "Generate or Re-Weight? A Mutual-Guidance Method for Class-Imbalanced Graphs"
authors:
  - "Zhongying Zhao"
  - "Gen Liu"
  - "Qi Meng"
  - "Chao Li"
  - "Qingtian Zeng"
doi: "10.24963/ijcai.2025/409"
url: "https://ijcai.org/proceedings/2025/409"
pdf: "https://ijcai.org/proceedings/2025/0409.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3680-3688"
track: "Main Track"
keywords:
  - "Data Mining: DM: Mining graphs"
  - "Data Mining: DM: Class imbalance and unequal cost"
---

# Generate or Re-Weight? A Mutual-Guidance Method for Class-Imbalanced Graphs

Zhongying Zhao, Gen Liu, Qi Meng, Chao Li, Qingtian Zeng

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3680-3688. DOI: [10.24963/ijcai.2025/409](https://doi.org/10.24963/ijcai.2025/409)

## Abstract

Class imbalance is a widespread problem in graph-structured data. The existing studies tailored for class-imbalanced graphs are typically categorized into generative and re-weighting methods. However, the former merely focuses on quantity balance rather than learning balance. The latter performs the fine-tuning in a majority-minority paradigm, overlooking the authentic-generative one. In fact, the collaboration of them is capable of relieving their respective limitations. To this end, we propose a Mutual-Guidance method for class-imbalanced graphs, namely GraphMuGu. Specifically, we first design an uncertainty-aware method to quantify the number of synthesized samples for each category. Furthermore, we devise a similarity-aware method to re-weight the importance of the authentic and generative samples. To the best our knowledge, the proposed GraphMuGu is the first try to incorporate the generative and re-weighting methods into a unified framework. The experimental results on five class-imbalanced datasets demonstrate the superiority of the proposed method. The source codes are available at https://github.com/ZZY-GraphMiningLab/GraphMuGu.