Research map / Graph learning / GNN architectures
NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| remove input k-NN graph (drop edge loss and relational bias) (ablation) | NodeFormer · Mini-ImageNet | accuracy: 86.77 -> 87.46 | Helped |
| remove input k-NN graph (drop edge loss and relational bias) (ablation) | NodeFormer · 20News-Groups | accuracy: 66.01 -> 64.71 (k=5); 64.55 -> 64.71 (k=20) | Mixed |
| replace Gumbel-Softmax with plain Softmax (NodeFormer-dt / -tp) (ablation) | NodeFormer · large-scale datasets | performance | Hurt |
| add edge-level regularization and relational bias (ablation) | NodeFormer · node classification datasets | performance | Helped |
| use NodeFormer's learned latent graphs instead of GCN on k-NN graph | GCN · Mini-ImageNet (k=5) | accuracy: 84.86 -> 86.77 | Helped |
| increase temperature from low to high (ablation) | NodeFormer · node classification | test accuracy | Mixed |
| increase random feature dimension m (ablation) | NodeFormer · node classification | test accuracy | Mixed |
Closest papers by meaning
- Graph Transformer Networks (NeurIPS 2019 · similarity 0.92)
- NLGT: Neighborhood-based and Label-enhanced Graph Transformer Framework for Node Classification (AAAI 2025 · similarity 0.90)
- Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification (NeurIPS 2024 · similarity 0.90)
- Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers (NeurIPS 2024 · similarity 0.90)
- What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding (ICML 2024 · similarity 0.89)
- Towards Dynamic Message Passing on Graphs (NeurIPS 2024 · similarity 0.89)
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.