Research map / Graph learning / GNN architectures
Node-Oriented Spectral Filtering for Graph Neural Networks
Shuai Zheng, Zhenfeng Zhu, Zhizhe Liu, Youru Li, Yao Zhao
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 node-oriented filtering (ablation) | Chebyshev-basis spectral GNN · Cora | accuracy (%): 76.07 -> 77.69 | Improved |
| add node-oriented filtering (ablation) | Chebyshev-basis spectral GNN · Citeseer | accuracy (%): 65.11 -> 67.74 | Improved |
| add node-oriented filtering (ablation) | Chebyshev-basis spectral GNN · Pubmed | accuracy (%): 84.02 -> 85.07 | Improved |
| add node-oriented filtering (ablation) | Chebyshev-basis spectral GNN · Chameleon | accuracy (%): 68.48 -> 72.52 | Improved |
| add node-oriented filtering (ablation) | Chebyshev-basis spectral GNN · Actor | accuracy (%): 39.11 -> 40.62 | Improved |
| add node-oriented filtering (ablation) | Chebyshev-basis spectral GNN · Texas | accuracy (%): 92.47 -> 94.03 | Improved |
| add node-oriented filtering (ablation) | Monomial-basis spectral GNN · Texas | accuracy (%): 91.80 -> 91.47 | Hurt |
| add node-oriented filtering (ablation) | Monomial-basis spectral GNN · Pubmed | accuracy (%): 82.28 -> 84.79 | Improved |
| add node-oriented filtering (ablation) | Bernstein-basis spectral GNN · Chameleon | accuracy (%): 67.82 -> 69.93 | Improved |
| increase polynomial order K from 1 to 3 (ablation) | NFGNN · several datasets | accuracy | Improved |
| increase low-rank order d from 1 to 5 (ablation) | NFGNN · several datasets | accuracy | No clear effect |
| use node-oriented filter instead of global filters (GPRGNN, BernNet) | NFGNN · Chameleon (full-supervised) | accuracy (%): 67.48 -> 72.52 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BernNet — BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation (NeurIPS 2021) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles (NeurIPS 2024 · similarity 0.91)
- SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter (ICML 2024 · similarity 0.91)
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (ICLR 2025 · similarity 0.90)
- HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations (NeurIPS 2025 · similarity 0.90)
- Spatio-Spectral Graph Neural Networks (NeurIPS 2024 · similarity 0.89)
- How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing (ICML 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.
