Research map / Graph learning / GNN architectures
GIER: Addressing Class Imbalance in GNNs Through Experience Replay
Liu Yang, Chuyao Liu, Zidong Wang, Tingxuan Chen, Mengni Chen, Hongyu Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Long-term Subgraph Memory (ablation) | GIER with GCN · CiteSeer (imbalance ratio 10) | BAcc: 39.90 -> 66.97 | Improved |
| add Long-term Subgraph Memory (ablation) | GIER with GCN · Cora (imbalance ratio 10) | BAcc: 63.16 -> 74.44 | Improved |
| add Short-term Confidence Calibration (ablation) | GIER with GCN · CiteSeer (imbalance ratio 10) | BAcc: 57.15 -> 66.97 | Improved |
| add Short-term Confidence Calibration (ablation) | GIER with GCN · PubMed (imbalance ratio 10) | BAcc: 75.39 -> 74.10 | Hurt |
| add Long-term Subgraph Memory (ablation) | GIER with SAGE · PubMed (imbalance ratio 10) | BAcc: 76.37 -> 76.38 | Hurt |
| filter top 10% confident nodes before SCC (LS variant) on PubMed (ablation) | GIER · PubMed (imbalance ratio 10) | BAcc: GCN 74.10 -> 75.46; SAGE 76.38 -> 77.24 | Mixed |
| use GIER (Full) instead of BAT(g-ens) | GCN · CiteSeer (imbalance ratio 10) | BAcc: 63.81 -> 66.97 | Improved |
| use GIER (Full) instead of BAT(g-ens) | GCN · PubMed (imbalance ratio 10) | BAcc: 75.38 -> 74.10 | Hurt |
| apply GIER across imbalance ratios 2,4,6,8,20 | GIER · Cora/CiteSeer/PubMed | BAcc | Improved |
Closest papers by meaning
- Class-Imbalanced Graph Learning without Class Rebalancing (ICML 2024 · similarity 0.89)
- IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning (ICLR 2025 · similarity 0.89)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.88)
- Cluster-guided Contrastive Class-imbalanced Graph Classification (AAAI 2025 · similarity 0.87)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.87)
- GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
