Research map / Graph learning / Graph self-supervised learning
Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks
Feng Ji, See Hian Lee, Hanyang Meng, Kai Zhao, Jielong Yang, Wee Peng Tay
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 both label-non-uniformity modules to GraphCON | GraphCON · Cora | accuracy: 82.36\pm 0.84 -> 85.23\pm 0.69 | Improved |
| Add both label-non-uniformity modules to ACM-GCN | ACM-GCN · Chameleon | accuracy: 65.92\atop\pm 2.32 -> 80.79} \atop\pm 1.95 | Improved |
| Add edge dropping to training-set supplementation (ablation) | wGNN (GCN) · Photo | accuracy: 91.93 \pm 0.25 -> 92.35 \pm 0.18 | Improved |
| Add edge dropping to training-set supplementation (ablation) | wGNN (GCN) · CS | accuracy: 89.29 \pm 0.14 -> 89.29 \pm 0.14 | No clear effect |
| Add edge dropping to training-set supplementation (ablation) | wGNN (GCN) · Cora | accuracy: 82.88 \pm 0.41 -> 83.12 \pm 0.31 | Improved |
| Add edge dropping to training-set supplementation (ablation) | wGNN (GCN) · Citeseer | accuracy: 73.55 \pm 0.46 -> 73.95 \pm 0.46 | Improved |
| Add training-set supplementation to edge dropping (ablation) | wGNN (GCN) · Cora | accuracy: 81.10 \pm 0.25 -> 83.12 \pm 0.31 | Improved |
| Add training-set supplementation to edge dropping (ablation) | wGNN (GCN) · Citeseer | accuracy: 71.98 \pm 0.52 -> 73.95 \pm 0.46 | Improved |
| Add training-set supplementation to edge dropping (ablation) | wGNN (GCN) · Pubmed | accuracy: 79.19 \pm 0.37 -> 80.48 \pm 0.25 | Improved |
| Add training-set supplementation to edge dropping (ablation) | wGNN (GCN) · Airport | accuracy: 86.07 \pm 1.52 -> 87.77 \pm 1.57 | Improved |
| Add training-set supplementation to edge dropping (ablation) | wGNN (GCN) · CS | accuracy: 88.54 \pm 0.37 -> 89.29 \pm 0.14 | Improved |
Closest papers by meaning
- Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily (NeurIPS 2023 · similarity 0.90)
- Combining Label Propagation and Simple Models out-performs Graph Neural Networks (ICLR 2021 · similarity 0.90)
- Beyond Fixed Depth: Adaptive Graph Neural Networks for Node Classification Under Varying Homophily (AAAI 2026 · similarity 0.89)
- Label-free Node Classification on Graphs with Large Language Models (LLMs) (ICLR 2024 · similarity 0.88)
- Normalize Then Propagate: Efficient Homophilous Regularization for Few-Shot Semi-Supervised Node Classification (AAAI 2025 · similarity 0.88)
- NLGT: Neighborhood-based and Label-enhanced Graph Transformer Framework for Node Classification (AAAI 2025 · similarity 0.88)
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.
