Research map / Graph learning / Graph algorithms and clustering
Tensor Power Iteration for Multi-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 |
|---|---|---|---|
| combine high-order node affinity with hyper-edge affinity rather than using either alone (ablation) | Tensor-MGM · CMU-House 4-graph | accuracy: 90.5 -> 96.6; 89.4 -> 96.6 | Helped |
| combine high-order node affinity with hyper-edge affinity rather than using either alone (ablation) | Tensor-MGM · WILLOW-Car 4-graph | accuracy: 62.2 -> 79.5; 68.7 -> 79.5 | Helped |
| combine high-order node affinity with hyper-edge affinity rather than using either alone (ablation) | Tensor-MGM · WILLOW-Winebottle 4-graph | accuracy: 81.2 -> 97.0; 82.7 -> 97.0 | Helped |
| combine high-order node affinity with hyper-edge affinity rather than using either alone (ablation) | Tensor-MGM · Building 4-graph | accuracy: 82.8 -> 92.8; 87.3 -> 92.8 | Helped |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · CMU-House 4-graph | accuracy: 99.0 -> 96.6 | Hurt |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · CMU-Hotel 12-graph | accuracy: 88.1 -> 97.9 | Helped |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · WILLOW-Car 12-graph | accuracy: 80.5 -> 67.1 | Hurt |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · WILLOW-Motorbike 4-graph | accuracy: 78.4 -> 87.5 | Helped |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · WILLOW-Motorbike 12-graph | accuracy: 87.1 -> 80.3 | Hurt |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · WILLOW-Winebottle 4-graph | accuracy: 71.2 -> 97.0 | Helped |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · WILLOW-Duck 12-graph | accuracy: 72.7 -> 58.3 | Hurt |
| use Tensor-MGM instead of the strongest listed baseline | multi-graph matching · Building 10-graph | accuracy: 87.3 -> 90.7 | Helped |
Closest papers by meaning
- Alternating Direction Graph Matching (CVPR 2017 · similarity 0.88)
- CURSOR: Scalable Mixed-Order Hypergraph Matching with CUR Decomposition (CVPR 2024 · similarity 0.87)
- Learning Combinatorial Solver for Graph Matching (CVPR 2020 · similarity 0.87)
- FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing (NeurIPS 2025 · similarity 0.87)
- Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS (ICML 2024 · similarity 0.86)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.86)
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.