Research map / Graph learning / Graph algorithms and clustering
Outlier-Robust Gromov-Wasserstein for Graph Data
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 |
|---|---|---|---|
| Use RGW instead of UGW | Subgraph alignment · Synthetic | matching accuracy: 89.88 -> 94.44 | Helped |
| Use RGW instead of BAPG | Subgraph alignment · Proteins-1 | matching accuracy: 30.98 -> 53.30 | Helped |
| Use RGW instead of UGW | Subgraph alignment · Proteins-2 | matching accuracy: 67.30 -> 69.38 | Helped |
| Use RGW instead of UGW | Subgraph alignment · Enzymes | matching accuracy: 43.73 -> 63.43 | Helped |
| Use RGW instead of BPG | Douban Online-Offline · Douban Online-Offline | Hit@1: 72.72 -> 75.58 | Helped |
| Use RGW instead of BAPG | Douban Online-Offline · Douban Online-Offline | Hit@10: 92.58 -> 96.24 | Helped |
| Set marginal relaxation rho above zero rather than rho = 0 (ablation) | RGW · Enzymes subgraph alignment | matching accuracy | Helped |
| Set rho excessively large or too small (ablation) | RGW · Enzymes subgraph alignment | matching accuracy | Hurt |
| Vary marginal penalty tau beyond the stable range (ablation) | RGW · Synthetic, Proteins, and Enzymes subgraph alignment | matching accuracy | Mixed |
| Use RGW instead of PGW | Partial shape correspondence on TOSCA · TOSCA | matching performance | Helped |
Closest papers by meaning
- LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate Descent (ICML 2026 · similarity 0.89)
- Partial Gromov-Wasserstein Metric (ICLR 2025 · similarity 0.89)
- Linear Partial Gromov-Wasserstein Embedding (ICLR 2025 · similarity 0.86)
- A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions (ICML 2024 · similarity 0.86)
- Graph Mixup on Approximate Gromov–Wasserstein Geodesics (ICML 2024 · similarity 0.85)
- ROG_PL: Robust Open-Set Graph Learning via Region-Based Prototype Learning (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.