Research map / Graph learning / GNN architectures
Graph Wavelet Neural Network
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 |
|---|---|---|---|
| replace Fourier transform with graph wavelet transform | Spectral CNN · Cora | accuracy: 73.3% -> 82.8% | Helped |
| replace Fourier transform with graph wavelet transform | Spectral CNN · Citeseer | accuracy: 58.9% -> 71.7% | Helped |
| replace Fourier transform with graph wavelet transform | Spectral CNN · Pubmed | accuracy: 73.9% -> 79.1% | Helped |
| use graph wavelet convolution instead of polynomial spectral filtering | ChebyNet · Cora | accuracy: 81.2% -> 82.8% | Helped |
| use graph wavelet convolution instead of polynomial spectral filtering | ChebyNet · Citeseer | accuracy: 69.8% -> 71.7% | Helped |
| use graph wavelet convolution instead of polynomial spectral filtering | ChebyNet · Pubmed | accuracy: 74.4% -> 79.1% | Helped |
| use graph wavelet convolution instead of GCN filtering | GCN · Cora | accuracy: 81.5% -> 82.8% | Helped |
| use graph wavelet convolution instead of GCN filtering | GCN · Citeseer | accuracy: 70.3% -> 71.7% | Helped |
| use graph wavelet convolution instead of GCN filtering | GCN · Pubmed | accuracy: 79.0% -> 79.1% | Helped |
| detach feature transformation from graph convolution (ablation) | ChebyNet · Cora | accuracy: 81.2% -> 81.6% | Helped |
| detach feature transformation from graph convolution (ablation) | ChebyNet · Citeseer | accuracy: 69.8% -> 68.5% | Hurt |
| detach feature transformation from graph convolution (ablation) | ChebyNet · Pubmed | accuracy: 74.4% -> 78.6% | Helped |
Closest papers by meaning
- SEA-GWNN: Simple and Effective Adaptive Graph Wavelet Neural Network (AAAI 2024 · similarity 0.90)
- A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition (ICML 2025 · similarity 0.89)
- WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets (AAAI 2024 · similarity 0.89)
- ASWT-SGNN: Adaptive Spectral Wavelet Transform-Based Self-Supervised Graph Neural Network (AAAI 2024 · similarity 0.88)
- Generalizing CNNs to graphs with learnable neighborhood quantization (NeurIPS 2024 · similarity 0.86)
- SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter (ICML 2024 · 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.