Research map / Graph learning / Graph algorithms and clustering
Generalizing Graph Matching beyond Quadratic Assignment Model
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 Separable Function (Laplacian) path following GGMlp instead of FGM | FGM · Caltech-101/MSRC natural images | accuracy (%): 76.35 -> 76.69 | Helped |
| use GGMlp instead of BPM on objective score ratio | BPM · Caltech-101/MSRC natural images | score ratio: 1 -> 0.972 | Hurt |
| shrink theta faster (alpha 0.5 -> 0.3) in path following (ablation) | GGM hPoly · Random graph matching | accuracy: 0.904 -> 0.725 | Hurt |
| shrink theta faster (alpha 0.5 -> 0.3) in path following (ablation) | GGM hLap · Random graph matching | accuracy: 0.906 -> 0.567 | Hurt |
| larger alpha (0.5 -> 0.7) at theta0=2 (ablation) | GGM hPoly · Random graph matching | accuracy: 0.904 -> 0.905 | No clear effect |
| start with smaller theta0 (2 -> 0.5) at alpha 0.5 (ablation) | GGM hPoly · Random graph matching | accuracy: 0.904 -> 0.770 | Hurt |
| start with smaller theta0 (2 -> 1) at alpha 0.5 (ablation) | GGM hLap · Random graph matching | accuracy: 0.906 -> 0.810 | Hurt |
| multiplicative strategy instead of path following (ablation) | GGM · Random graph matching | accuracy | No clear effect |
| use multiplicative strategy instead of path following (ablation) | GGMlp · CMU house sequence | convergence speed | Helped |
| Laplacian vs polynomial Separable Function (ablation) | GGM · Random graph matching | accuracy | No clear effect |
Closest papers by meaning
- Alternating Direction Graph Matching (CVPR 2017 · similarity 0.90)
- Nonnegative Orthogonal Graph Matching (AAAI 2017 · similarity 0.89)
- FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing (NeurIPS 2025 · similarity 0.88)
- Graph Alignment via Birkhoff Relaxation (NeurIPS 2025 · similarity 0.87)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.86)
- Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS (ICML 2024 · similarity 0.85)
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.