The rapid advancement in data-driven research has increased the demand for
effective graph data analysis. However, real-world data often exhibits class
imbalance, leading to poor performance of machine learning m
Class-Incremental Learning faces a dual imbalance problem, which results in skewed gradient updates, catastrophic forgetting, and imbalanced forgetting, but these issues can be addressed using reweighting techniques and a distribution-aware knowledge distillation loss, leading to consistent improvements in performance.