Research map / Graph learning / GNN architectures
AdaSpec: Adaptive Spectrum for Enhanced Node Distinguishability
Fangbing Liu, Qing Wang
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 AdaSpec adaptive graph matrix | ChebNet · Texas | accuracy: 38.67 -> 51.16 | Improved |
| add AdaSpec | GPRGNN · Texas | accuracy: 48.15 -> 58.27 | Improved |
| add AdaSpec | GPRGNN · Questions | ROC AUC: 53.14 -> 58.19 | Improved |
| add AdaSpec | JacobiConv · Cora | accuracy: 77.15 -> 83.52 | Improved |
| add AdaSpec | spectral GNNs on heterophilic graphs · small heterophilic graphs | accuracy: 1.89% | Improved |
| add AdaSpec | spectral GNNs on homophilic graphs · homophilic graphs | accuracy: 0.43% | No clear effect |
| add AdaSpec | ChebNet · Squirrel | accuracy: 24.23 -> 23.2 | Hurt |
| add AdaSpec | ChebNet · Tolokers | ROC AUC: 70.1 -> 69.2 | Hurt |
| add AdaSpec | ChebNet · Roman_Empire | accuracy: 47.15 -> 54.55 | Improved |
| add all three components (full Omega(A,X)) versus Omega_D(A) alone (ablation) | ChebNet · Texas | accuracy: 40.75 -> 51.16 | Improved |
| add Omega_D(A) and Omega_F(X) to Omega_S(A) (ablation) | ChebNet · Cora | accuracy: 55.63 -> 82.26 | Improved |
| use Omega_D instead of Omega_S on structure-dominated graph (ablation) | ChebNet · Cora | accuracy: 55.63 -> 81.53 | 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 1 of 1 shared result
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
- On the Expressive Power of Spectral Invariant Graph Neural Networks (ICML 2024 · similarity 0.90)
- Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum (NeurIPS 2025 · similarity 0.89)
- Enhancing Spectral GNNs: From Topology and Perturbation Perspectives (ICML 2025 · similarity 0.89)
- Improving Distinguishability of Class for Graph Neural Networks (AAAI 2024 · similarity 0.89)
- Homomorphism Expressivity of Spectral Invariant Graph Neural Networks (ICLR 2025 · similarity 0.89)
- Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correction (AAAI 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.
