Research map / Graph learning / GNN architectures
GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
Mingxuan Ju, Tong Zhao, Wenhao Yu, Neil Shah, Yanfang Ye
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 GraphPatcher test-time patching to GCN | GCN · Cora (low-degree nodes) | accuracy: 73.27 -> 78.08 | Improved |
| add GraphPatcher test-time patching to GCN | GCN · Cora (overall) | accuracy: 81.22 -> 84.17 | Improved |
| add GraphPatcher to GCN | GCN · Cora (high-degree nodes) | accuracy: 86.83 -> 88.02 | Improved |
| add TuneUp to GCN | GCN · Amazon-Photo (high-degree nodes) | accuracy: 84.07 -> 81.57 | Hurt |
| add ColbBrew to GCN | GCN · Wiki.CS (high-degree nodes) | accuracy: 83.40 -> 71.98 | Hurt |
| add Tail-GNN to GCN | GCN · Cora (high-degree nodes) | accuracy: 86.83 -> 84.13 | Hurt |
| add EERM or GTrans (OOD frameworks) to GCN | GCN · degree-bias benchmarks | accuracy | No clear effect |
| apply GraphPatcher to GraphSAGE | GraphSAGE · Cora (low-degree nodes) | accuracy: 70.57 -> 72.33 | Improved |
| apply GraphPatcher to GAT | GAT · Cora (low-degree nodes) | accuracy: 73.27 -> 76.88 | Improved |
| apply GraphPatcher to self-supervised DGI | DGI · Pubmed (low-degree nodes) | accuracy: 75.63 -> 78.04 | Improved |
| apply GraphPatcher to GRAND | GRAND · Pubmed (low-degree nodes) | accuracy: 80.48 -> 84.68 | Improved |
| increase number of test-time patching nodes (ablation) | GraphPatcher · Cora, Citeseer, Pubmed | overall accuracy | Improved |
Closest papers by meaning
- Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks (NeurIPS 2024 · similarity 0.89)
- Online GNN Evaluation Under Test-time Graph Distribution Shifts (ICLR 2024 · similarity 0.88)
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · similarity 0.87)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.87)
- AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs (AAAI 2024 · similarity 0.87)
- Generalization of Graph Neural Networks Is Robust to Model Mismatch (AAAI 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.
