Research map / Graph learning / GNN architectures
$p$-Laplacian Based Graph 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 |
|---|---|---|---|
| Use ¹.⁰GNN instead of the strongest listed baseline | Node classification · Chameleon | accuracy (%): 48.02 -> 48.86 | No clear effect |
| Use ¹.⁰GNN instead of the strongest listed baseline | Node classification · Squirrel | accuracy (%): 33.80 -> 33.75 | No clear effect |
| Use ¹.⁰GNN instead of the strongest listed baseline | Node classification · Actor | accuracy (%): 39.68 -> 40.62 | Helped |
| Use ¹.⁰GNN instead of the strongest listed baseline | Node classification · Wisconsin | accuracy (%): 93.56 -> 95.37 | No clear effect |
| Use ².⁰GNN instead of APPNP | Node classification · Texas | accuracy (%): 82.90 -> 87.96 | Helped |
| Use ¹.⁰GNN instead of the strongest listed baseline | Node classification · Cornell | accuracy (%): 80.30 -> 82.16 | No clear effect |
| Use ².⁰GNN rather than ¹.⁰GNN on heterophilic cSBM settings with φ ≤ -0.5 | pGNN · cSBM, sparse split | accuracy | Helped |
| Use ¹.⁵GNN on weakly homophilic cSBM settings | pGNN · cSBM, φ = 0.25, 0.5 | accuracy | Helped |
| Use pGNN instead of other GNN baselines on cSBM with nearly non-informative topology | Node classification · cSBM, φ = -0.25, 0 | accuracy | Helped |
| Use ¹.⁵GNN rather than other methods on Computers with completely random edges | Node classification · Computers, r = 1 | accuracy | No clear effect |
| Use pGNN instead of ordinary GNN baselines as random-edge rate increases | Node classification · Graphs with noisy edges | accuracy | Helped |
Closest papers by meaning
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (ICLR 2025 · similarity 0.90)
- Enhancing Spectral GNNs: From Topology and Perturbation Perspectives (ICML 2025 · similarity 0.89)
- HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations (NeurIPS 2025 · similarity 0.89)
- SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter (ICML 2024 · similarity 0.89)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.89)
- Improving Graph Neural Networks by Learning Continuous Edge Directions (ICLR 2025 · 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.