Research map / Graph learning / Graph algorithms and clustering
Semi-relaxed Gromov-Wasserstein divergence and applications on graphs
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 |
|---|---|---|---|
| Estimate the target graph node weights by relaxing its transport marginal | srGW graph partitioning · Wikipedia asym | AMI: 46.43 -> 56.92 | Helped |
| Estimate the target graph node weights by relaxing its transport marginal | srGW graph partitioning · Amazon sym | AMI: 94.33 -> 48.28 | Hurt |
| Add entropic regularization (ablation) | srGW partitioning · Wikipedia asym | AMI: 56.92 -> 57.13 | No clear effect |
| Add entropic regularization (ablation) | srGW partitioning · EU-email asym | AMI: 49.94 -> 54.75 | Helped |
| Add sparsity-promoting regularization (ablation) | srGW graph clustering · IMDB-B | Rand Index: 51.59(0.10) -> 52.44(0.46) | Helped |
| Add sparsity-promoting regularization (ablation) | srGW graph clustering · IMDB-M | Rand Index: 54.94(0.29) -> 56.70(0.34) | Helped |
| Add entropic regularization (ablation) | srGW graph clustering · MUTAG | Rand Index: 71.25(0.39) -> 74.41(0.84) | Helped |
| Add entropic and sparsity-promoting regularization (ablation) | srGW graph clustering · PTC-MR | Rand Index: 51.48(0.12) -> 52.53(0.47) | Helped |
| Add entropic and sparsity-promoting regularization (ablation) | srGW graph clustering · BZR | Rand Index: 62.60(0.96) -> 67.81(0.94) | Helped |
| Add sparsity-promoting regularization (ablation) | srGW graph clustering · COX2 | Rand Index: 60.12(0.27) -> 62.15(0.27) | Helped |
| Add sparsity-promoting regularization (ablation) | srGW graph clustering · ENZYMES | Rand Index: 71.68(0.12) -> 72.51(0.10) | Helped |
| Add entropic and sparsity-promoting regularization (ablation) | srGW graph clustering · PROTEIN | Rand Index: 59.66(0.10) -> 60.81(0.43) | Helped |
Closest papers by meaning
- Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching (NeurIPS 2019 · similarity 0.92)
- Online Graph Dictionary Learning (ICML 2021 · similarity 0.92)
- Optimal Transport for structured data with application on graphs (ICML 2019 · similarity 0.90)
- Linear Partial Gromov-Wasserstein Embedding (ICLR 2025 · similarity 0.88)
- Generalized Sobolev Transport for Probability Measures on a Graph (ICML 2024 · similarity 0.87)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.87)
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.