Research map / Learning theory and algorithms / Optimal transport
Achieving Structurally Robust Gromov Wasserstein Distance via Adaptive Dual-Mask
Kangke Cheng, Jiawei Huang, Jingni Song, Wanlin Zhang, Bangxian Han, Hu Ding
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 Mask-Guided GW instead of RGW | Mask-Guided GW · ENZYMES subgraph alignment (rho=0.5) | node accuracy: +10.7% | Improved |
| use Mask-Guided GW instead of RGW | Mask-Guided GW · DHFR subgraph alignment (rho=0.5) | node accuracy: +11.1% | Improved |
| use Mask-Guided GW instead of UGW | Mask-Guided GW · Fingerprint structural noise (eta=0.1) | edge accuracy: 47.3 -> 60.8 | Improved |
| use Mask-Guided GW instead of RGW | Mask-Guided GW · ENZYMES subgraph alignment (rho=0.5) | runtime: 1142 -> 77.1 s | Improved |
| use Mask-Guided GW instead of UGW | Mask-Guided GW · Fingerprint subgraph alignment (rho=0.5) | node accuracy: 43.3 -> 47.5 | Mixed |
| vary noise budget epsilon on ENZYMES (ablation) | Mask-Guided GW · ENZYMES | matching accuracy | Mixed |
| increase subgraph ratio rho from 0.2 to 0.6 (ablation) | Mask-Guided GW · ENZYMES and DHFR | matching accuracy | Improved |
Closest papers by meaning
- Gromov-Wasserstein at Scale, Beyond Squared Norms (ICML 2026 · similarity 0.88)
- LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate Descent (ICML 2026 · similarity 0.88)
- Outlier-Robust Gromov-Wasserstein for Graph Data (NeurIPS 2023 · similarity 0.87)
- A Novel Sliced Fused Gromov-Wasserstein Distance (AAAI 2026 · similarity 0.87)
- Distance-Based Tree-Sliced Wasserstein Distance (ICLR 2025 · similarity 0.84)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.83)
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.
