Research map / Graph learning / Graph algorithms and clustering
Can Hybrid Geometric Scattering Networks Help Solve the Maximum Clique Problem?
Yimeng Min, Frederik Wenkel, Michael Perlmutter, Guy Wolf
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 band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · TWITTER | approximation score: 0.887 -> 0.952 | Improved |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · IMDB | approximation score: 0.956 -> 1.000 | Improved |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · COLLAB | approximation score: 0.981 -> 0.999 | Improved |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · LARGE-hard | approximation score: 0.829 -> 1.102 | Improved |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · LARGE-medium | approximation score: 0.925 -> 1.045 | Improved |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · LARGE-easy | approximation score: 0.997 -> 1.002 | No clear effect |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · SMALL-hard | approximation score: 0.776 -> 0.846 | Improved |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · SMALL-medium | approximation score: 0.873 -> 0.935 | Improved |
| add band-pass scattering filters to low-pass GCN (ablation) | ScatteringClique · SMALL-easy | approximation score: 0.951 -> 0.993 | Improved |
| replace Erdos GNN accurate with ScatteringClique | ScatteringClique · TWITTER | inference time (s/G): 0.42 -> 0.05 | Improved |
| replace RUN-CSP accurate with ScatteringClique | ScatteringClique · TWITTER | approximation score: 0.987 -> 0.952 | Hurt |
| increase Gurobi time budget from 0.1s to 0.5s | Gurobi 9.0 · TWITTER | approximation score: 0.803 -> 0.996 | Improved |
Closest papers by meaning
- Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering (NeurIPS 2024 · similarity 0.85)
- Are Graph Neural Networks Optimal Approximation Algorithms? (NeurIPS 2024 · similarity 0.84)
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · similarity 0.84)
- Unsupervised Parameter-free Simplicial Representation Learning with Scattering Transforms (ICML 2024 · similarity 0.84)
- A Fast Exact Solver with Theoretical Analysis for the Maximum Edge-Weighted Clique Problem (AAAI 2024 · similarity 0.84)
- Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models (NeurIPS 2025 · similarity 0.84)
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.
