Research map / Graph learning / Graph algorithms and clustering
Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
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 |
|---|---|---|---|
| Apply GWL instead of the strongest listed baseline | Graph partitioning · Synthetic partitioning, (4000, 0.2, 0.05), (4000, 0.2, 0.1), and (4000, 0.2, 0.15) | AMI: 0.747 -> 0.812; 0.574 -> 0.590; 0.005 -> 0.012 | Helped |
| Apply GWL instead of the strongest listed baseline | Graph partitioning · EU-Email raw | AMI: 0.434 -> 0.459 | Helped |
| Apply GWL instead of the strongest listed baseline | Graph partitioning · Indian-Village raw | AMI: 0.882 -> 0.857 | Hurt |
| Apply GWL instead of the strongest listed baseline | Graph partitioning · Indian-Village noisy | AMI: 0.633 -> 0.664 | Helped |
| Add the recursive partition mechanism to GWL | Graph matching · Yeast 5% noise | runtime (second): 190.97 -> 68.58 | Helped |
| Add the recursive partition mechanism to GWL | Graph matching · Yeast 5% noise | NC: 82.37 -> 81.08 | Hurt |
| Add the recursive partition mechanism to GWL | Graph matching · Yeast 15% noise | NC: 65.34 -> 61.85 | Hurt |
| Add the recursive partition mechanism to GWL | Graph matching · Yeast 25% noise | NC: 58.76 -> 56.27 | Mixed |
| Add the recursive partition mechanism to GWL | Graph matching · MC3 sparse | runtime (second): 89.43 -> 8.39 | Helped |
| Use node prior regularization with proximal gradient (ablation) | GW discrepancy optimization · Synthetic graphs with 1,000 nodes | GW discrepancy | Helped |
| Use non-uniform node distributions instead of uniform distributions (ablation) | Multi-graph partitioning and matching · Multi-graph partitioning | partition consistency | Helped |
Closest papers by meaning
- Gromov-Wasserstein Learning for Graph Matching and Node Embedding (ICML 2019 · similarity 0.93)
- Semi-relaxed Gromov-Wasserstein divergence and applications on graphs (ICLR 2022 · similarity 0.92)
- Gromov-Wasserstein Factorization Models for Graph Clustering (AAAI 2020 · similarity 0.92)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.89)
- A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening (ICML 2023 · similarity 0.89)
- M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering (ICLR 2024 · 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.