Research map / Graph learning / Graph algorithms and clustering
Wasserstein Graph Distance Based on L1–Approximated Tree Edit Distance between Weisfeiler–Lehman Subtrees
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 WWLS instead of the strongest listed baseline | Graph classification · MUTAG | accuracy: 87.77$\pm$0.81 -> 88.30$\pm$1.23 | Helped |
| Use WWLS instead of the strongest listed baseline | Graph classification · PTC-MR | accuracy: 66.31$\pm$1.21 -> 67.32$\pm$1.09 | Helped |
| Use WWLS instead of the strongest listed baseline | Graph classification · COX2 | accuracy: 82.08$\pm$0.93 -> 81.58$\pm$0.91 | Hurt |
| Use WWLS instead of the strongest listed baseline | Graph classification · ENZYMES | accuracy: 59.13$\pm$0.80 -> 63.35$\pm$1.14 | Helped |
| Use WWLS instead of the strongest listed baseline | Graph classification · PROTEINS | accuracy: 74.28$\pm$0.56 -> 75.35$\pm$0.74 | Helped |
| Use WWLS instead of the strongest listed baseline | Graph classification · NCI1 | accuracy: 86.40$\pm$0.20 -> 86.06$\pm$0.09 | Hurt |
| Use WWLS instead of the strongest listed baseline | Graph classification · BZR | accuracy: 87.43$\pm$0.81 -> 88.02$\pm$0.61 | Helped |
| Use WWLS instead of the strongest listed baseline | Graph classification · IMDB-B | accuracy: 74.37$\pm$0.83 -> 75.08$\pm$0.31 | Helped |
| Use WWLS instead of the strongest listed baseline | Graph classification · IMDB-M | accuracy: 50.25$\pm$0.72 -> 51.61$\pm$0.62 | Helped |
| Use WWLS instead of the strongest listed baseline | Graph classification · COLLAB | accuracy: 80.18$\pm$0.25 -> 82.81$\pm$0.16 | Helped |
Closest papers by meaning
- Weisfeiler-Lehman Meets Gromov-Wasserstein (ICML 2022 · similarity 0.91)
- UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein Distance (ICML 2025 · similarity 0.86)
- Generalizing Weisfeiler-Lehman Kernels to Subgraphs (ICLR 2025 · similarity 0.86)
- Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy (ICLR 2025 · similarity 0.85)
- On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters (ICLR 2024 · similarity 0.85)
- Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks (NeurIPS 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.