EUVIMEDEUVIMED entdecken
Crossref

GIER: Addressing Class Imbalance in GNNs Through Experience Replay

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

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (19) · 16110-16118

DOI: 10.1609/aaai.v40i19.38646 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Liu Yang und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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's ability to mine minority node information in historical data, thereby achieving feature completion for minority class nodes. On the other hand, the proposed short-term confidence mechanism allows the model to adaptively calibrate the topological relationships in high-confidence nodes, thereby mitigating the model's tendency to propagate erroneous information about minority classes during training. GIER is a unified framework consisting of two synergistic components: Long-term Subgraph Memory (LSM) constructs multi-period feature-representative subgraphs to address distribution imbalance, and Short-term Confidence Calibration (SCC) dynamically reconstructs graph topology through degree-aware node selection and confidence-based filtering to address topological imbalance. The extensive experimental results demonstrate that GIER effectively improves the classification performance of GNNs on imbalanced graphs, achieving up to a 3.44% improvement in BAcc over the state-of-the-art, and is particularly effective in extreme scenarios with very small minority classes.

Zitieren

APA

Yang, L., Liu, C., Wang, Z., Chen, T., Chen, M., & Zhang, H. (2026). GIER: Addressing Class Imbalance in GNNs Through Experience Replay. Proceedings of the AAAI Conference on Artificial Intelligence, 40(19), 16110-16118. https://doi.org/10.1609/aaai.v40i19.38646

Vancouver

Yang L, Liu C, Wang Z, Chen T, Chen M, Zhang H. GIER: Addressing Class Imbalance in GNNs Through Experience Replay. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(19):16110-16118. doi:10.1609/aaai.v40i19.38646

BibTeX
@article{Yang2026,
  author = {Yang, Liu and Liu, Chuyao and Wang, Zidong and Chen, Tingxuan and Chen, Mengni and Zhang, Hongyu},
  title = {GIER: Addressing Class Imbalance in GNNs Through Experience Replay},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {19},
  pages = {16110--16118},
  doi = {10.1609/aaai.v40i19.38646}
}
Kostenlos starten →