Research map / Graph learning / Graph algorithms and clustering
Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning
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 unsupervised learning from GA-MGMC pseudo labels (GANN-MGMC vs learning-free GA-MGMC) | GA-MGMC · Willow MGMC 8 Cars, 8 Ducks, 8 Motorbikes | matching accuracy: 0.653 -> 0.896 | Helped |
| add unsupervised learning from GA-MGMC pseudo labels | GA-MGMC · Willow MGMC 40 Cars, 50 Ducks, 40 Motorbikes | clustering purity: 0.890 -> 0.974 | Helped |
| add unsupervised learning from GA-MGMC pseudo labels | GA-MGMC · CUB2011 MGMC | clustering and matching metrics | Helped |
| unsupervised GANN-MGM instead of learning-free GA-MGM | GA-MGM · Willow MGM car | matching accuracy: 0.746 -> 0.964 | Helped |
| unsupervised GANN-MGM instead of learning-free GA-MGM | GA-MGM · Willow MGM mbike | matching accuracy: 0.892 -> 1.000 | Helped |
| gradually decrease clustering weight beta from 1 to 0 (ablation) | GA-MGMC · Willow MGMC 40 Cars, 50 Ducks, 40 Motorbikes | matching and clustering accuracy | Helped |
| unsupervised GANN-MGMC vs DPMC on larger problem | MGMC · Willow MGMC 40 Cars, 50 Ducks, 40 Motorbikes | matching accuracy: 0.906 vs 0.941 | Mixed |
| unsupervised training vs supervised training on CUB2011 generalization | GANN-MGM · CUB2011 MGM | test f1-score | 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)
- Learning Combinatorial Solver for Graph Matching (CVPR 2020 · similarity 0.90)
- Multiple Graph Matching and Clustering via Decayed Pairwise Matching Composition (AAAI 2020 · similarity 0.89)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.88)
- Discrete Cycle-Consistency Based Unsupervised Deep Graph Matching (AAAI 2024 · 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.