Research map / Learning theory and algorithms / Optimal transport
Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation
Junhyoung Chung, Euijong Song, Won Hwa Kim, Gunwoong Park
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 CDOT instead of FGW | graph matching · Synthetic clustered point clouds (n=100) | MSE: 0.0146 -> 0.0077 | Improved |
| increase sample size n from 100 to 500 | CDOT · Synthetic clustered point clouds | MSE: 0.0077 -> 0.0016 | Improved |
| use CDOT instead of EFGW | graph matching · Synthetic clustered point clouds (n=500) | MSE: 0.0025 -> 0.0016 | Improved |
| use CDOT instead of FGW with diffusion distance | node matching · OASIS-3 matching (diffusion distance) | accuracy: 0.1853 -> 0.6136 | Improved |
| use CDOT instead of FGW with geodesic distance | node matching · OASIS-3 matching (geodesic distance) | accuracy: 0.5375 -> 0.4640 | Hurt |
| use diffusion instead of geodesic distance for CDOT | CDOT · OASIS-3 matching | accuracy: 0.4640 -> 0.6136 | Improved |
| use diffusion instead of geodesic distance for FGW | FGW · OASIS-3 matching | accuracy: 0.5375 -> 0.1853 | Hurt |
| use CDOT instead of FGW as graph distance | SVM graph classification · ENZYMES graph classification | accuracy: 0.4450 -> 0.5133 | Improved |
| use CDOT instead of FGW as graph distance | SVM graph classification · MUTAG graph classification | accuracy: 0.8249 -> 0.8617 | Improved |
| use CDOT instead of COPT without node features | SVM graph classification · IMDB-B graph classification | accuracy: 0.6370 -> 0.6420 | Improved |
Closest papers by meaning
- Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation (NeurIPS 2026 · similarity 0.88)
- CO-Optimal Transport (NeurIPS 2020 · similarity 0.88)
- Regularized Optimal Transport and the Rot Mover's Distance (JMLR 2018 · similarity 0.88)
- Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data (ICLR 2025 · similarity 0.86)
- Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformer (ICML 2024 · similarity 0.86)
- Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization (ICML 2025 · 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.
