GIER: Addressing Class Imbalance in GNNs Through Experience Replay

Liu Yang; Chuyao Liu; Zidong Wang; Tingxuan Chen; Mengni Chen; Hongyu Zhang

AAAI 2026technical0 citations

GIER: Addressing Class Imbalance in GNNs Through Experience Replay

Liu Yang, Chuyao Liu, Zidong Wang, Tingxuan Chen, Mengni Chen, Hongyu Zhang

Abstract

The prevalent class imbalance in real-world graphs significantly affects the performance of Graph Neural Networks (GNNs). Existing methods for analyzing graph imbalance ignore the influence of minority nodes during the dynamic model training process, resulting in performance limitations. In this paper, we focus on minority class information during model training, identifying and defining the minority class forgetting phenomenon that exists in graph imbalanced method training processes. To address this issue, we propose Graph Imbalance Experience Replay(GIER) framework. On one hand, the method enhances the model

BibTeX

@inproceedings{aaai2026_gieraddressingcl,
  title = {GIER: Addressing Class Imbalance in GNNs Through Experience Replay},
  author = {Liu Yang and Chuyao Liu and Zidong Wang and Tingxuan Chen and Mengni Chen and Hongyu Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}