Research map / Graph learning / GNN architectures
GSSNN: Graph Smoothing Splines Neural Networks
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 |
|---|---|---|---|
| add S3 smoothing module to GCN | GCN · MUTAG | accuracy (%): 93.50 -> 96.77 | Helped |
| add S3 smoothing module to GCN | GCN · IMDB-M | accuracy (%): 54.33 -> 59.00 | Helped |
| add S3 smoothing module to GCN | GCN · DD | accuracy (%): 77.76 -> 80.26 | Helped |
| add S3 smoothing module to GAT | GAT · IMDB-M | accuracy (%): 55.33 -> 56.67 | Helped |
| add S3 smoothing module to GAT | GAT · DD | accuracy (%): 77.78 -> 81.20 | Helped |
| add degree centrality to self-attention node scoring (ablation) | GSSNN · MUTAG | accuracy (%): 88.89 -> 94.44 | Helped |
| add closeness centrality to scoring (ablation) | GSSNN · MUTAG | accuracy (%): 94.44 -> 96.77 | Helped |
| add closeness centrality to scoring (ablation) | GSSNN · DD | accuracy (%): 77.78 -> 80.26 | Helped |
| add closeness centrality to scoring (ablation) | GSSNN · IMDB-B | accuracy (%): 79.30 -> 80.10 | Helped |
| GSSNN vs strongest baseline | GSSNN · NCI1 | accuracy (%): 82.19 -> 80.75 | Mixed |
| GSSNN vs GIN | GSSNN · IMDB-M | accuracy (%): 54.33 -> 59.00 | Helped |
Closest papers by meaning
- Measuring and Relieving the Over-Smoothing Problem for Graph Neural Networks from the Topological View (AAAI 2020 · similarity 0.91)
- Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module (NeurIPS 2024 · similarity 0.87)
- Improving Graph Neural Networks by Learning Continuous Edge Directions (ICLR 2025 · similarity 0.87)
- Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness (ICML 2024 · similarity 0.86)
- Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence (ICML 2025 · similarity 0.86)
- Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective (NeurIPS 2025 · similarity 0.86)
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.