Research map / Graph learning / GNN architectures
Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
Kenta Oono, Taiji Suzuki
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 end-to-end fine-tuning to GB-GNN-Adj (ablation) | GB-GNN-Adj · Cora | accuracy (%): 79.9 \pm 0.8 -> 80.4 \pm 0.8 | Improved |
| Add end-to-end fine-tuning to GB-GNN-Adj (ablation) | GB-GNN-Adj · CiteSeer | accuracy (%): 70.5 \pm 0.8 -> 70.8 \pm 0.8 | Improved |
| Add end-to-end fine-tuning to GB-GNN-Adj (ablation) | GB-GNN-Adj · PubMed | accuracy (%): 79.4 \pm 0.2 -> 79.0 \pm 0.5 | Hurt |
| Add end-to-end fine-tuning to GB-GNN-KTA (ablation) | GB-GNN-KTA · Cora | accuracy (%): 80.9 \pm 0.9 -> 82.3 \pm 1.1 | Improved |
| Add end-to-end fine-tuning to GB-GNN-KTA (ablation) | GB-GNN-KTA · CiteSeer | accuracy (%): 73.1 \pm 1.1 -> 70.8 \pm 1.0 | Hurt |
| Add end-to-end fine-tuning to GB-GNN-KTA (ablation) | GB-GNN-KTA · PubMed | accuracy (%): 79.1 \pm 0.4 -> N.A. | Mixed |
| Use KTA aggregation instead of augmented-adjacency aggregation | GB-GNN · Cora | accuracy (%): 79.9 \pm 0.8 -> 80.9 \pm 0.9 | Improved |
| Use KTA aggregation instead of augmented-adjacency aggregation | GB-GNN · CiteSeer | accuracy (%): 70.5 \pm 0.8 -> 73.1 \pm 1.1 | Improved |
| Use KTA aggregation instead of augmented-adjacency aggregation | GB-GNN · PubMed | accuracy (%): 79.4 \pm 0.2 -> 79.1 \pm 0.4 | Hurt |
Closest papers by meaning
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.89)
- Dynamic Rescaling for Training GNNs (NeurIPS 2024 · similarity 0.89)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.88)
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · similarity 0.88)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.88)
- Learning to Reweight for Generalizable Graph Neural Network (AAAI 2024 · 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.
