Research map / Graph learning / Graph algorithms and clustering
Multiple Graph Matching and Clustering via Decayed Pairwise Matching Composition
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 |
|---|---|---|---|
| add decayed pairwise matching composition (DPMC-A) on top of raw pairwise matching | RRWM · Willow multi-cluster | matching accuracy: 0.715 -> 0.887 | Helped |
| DPMC-A vs CAO-C | multi-cluster graph matching · synthetic multi-cluster | clustering accuracy: 0.676 -> 0.765 | Helped |
| DPMC-A vs CAO-PC | multi-cluster graph matching · Willow multi-cluster | matching accuracy: 0.843 -> 0.887 | Helped |
| apply DPMC to RRWM-initialized affinity (ablation) | DPMC · multi-cluster clustering | clustering accuracy: 0.541 -> 0.731 | Helped |
| apply DPMC to MatchOpt-initialized affinity (ablation) | DPMC · multi-cluster clustering | clustering accuracy: 0.351 -> 0.350 | No clear effect |
| increase constant decay rate above 0.7 (ablation) | DPMC-C · Willow and synthetic multi-cluster | matching accuracy: MA drops about 0.1 (real) and 0.2 (synthetic) | Hurt |
| tree-based composition (TPMC) instead of MatchOpt star structure | single-cluster multi-graph matching · Willow car, synthetic deform | accuracy: about 11% to 19% | Helped |
| TPMC instead of CAO-PC | single-cluster multi-graph matching · all single-cluster datasets | accuracy: 1% to 2% accuracy loss, nearly 2x faster | Mixed |
Closest papers by meaning
- M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering (ICLR 2024 · similarity 0.90)
- Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning (NeurIPS 2020 · similarity 0.89)
- A Convex Relaxation for Multi-Graph Matching (CVPR 2019 · similarity 0.89)
- Learning Combinatorial Solver for Graph Matching (CVPR 2020 · similarity 0.87)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.86)
- Discrete Cycle-Consistency Based Unsupervised Deep Graph Matching (AAAI 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.