Research map / Graph learning / Graph algorithms and clustering
Alternating Direction Graph Matching
Check 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 ADGM instead of DD | Pairwise model A · House | Time (s): 14.20 -> 0.03 | Helped |
| Use ADGM instead of DD | Pairwise model A · Hotel | Time (s): 13.57 -> 0.02 | Helped |
| Use ADGM rather than MPM, RRWM, IPFP, or SMAC | Pairwise model B · House and Hotel, occlusion-allowed tests | Objective value | Helped |
| Use ADGM rather than pairwise baselines | Pairwise model C · Cars and Motorbikes | Objective value | Helped |
| Use ADGM1 or ADGM2 rather than other higher-order methods | Third-order model · House | Objective value | Mixed |
| Use ADGM1 or ADGM2 rather than BCAGM | Third-order model · Cars | Objective value: 7/9 cases | Helped |
| Use ADGM1 rather than BCAGM | Third-order model · Motorbikes | Objective value: 5/9 cases; 1/9 cases | Mixed |
| Use ADGM2 rather than BCAGM | Third-order model · Motorbikes | Objective value: 8/9 cases | Helped |
| Use ADGM1 instead of ADGM2 (ablation) | Third-order ADGM · House | Performance | No clear effect |
| Replace pairwise model B with the proposed pairwise model C | Graph matching on Cars and Motorbikes · Cars and Motorbikes | Matching results | Helped |
Closest papers by meaning
- Generalizing Graph Matching beyond Quadratic Assignment Model (NeurIPS 2018 · similarity 0.90)
- FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing (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 0.86)
- Graph Alignment via Birkhoff Relaxation (NeurIPS 2025 · similarity 0.85)
- SAT-Based Algorithms for Regular Graph Pattern Matching (AAAI 2024 · 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.