Research map / Graph learning / Graph self-supervised learning
Deep Wasserstein Graph Discriminant Learning for Graph Classification
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 |
|---|---|---|---|
| add a dynamic Wasserstein graph dictionary (ablation) | 3-layer GCN · PROTEINS | accuracy: 75.85±2.97 -> 77.29±2.91 | Helped |
| add a dynamic Wasserstein graph dictionary (ablation) | 3-layer GCN · IMDB-BINARY | accuracy: 77.30±3.20 -> 79.70±3.59 | Helped |
| add the optimal transport projection to W-distance (ablation) | WGDL No OT · PROTEINS | accuracy: 73.51±3.84 -> 77.29±2.91 | Helped |
| add the optimal transport projection to W-distance (ablation) | WGDL No OT · IMDB-BINARY | accuracy: 77.40±2.99 -> 79.70±3.59 | Helped |
| add the WD-Loss (ablation) | WGDL No WD · PROTEINS | accuracy: 76.39±2.68 -> 77.29±2.91 | Helped |
| add the WD-Loss (ablation) | WGDL No WD · IMDB-BINARY | accuracy: 78.70±3.65 -> 79.70±3.59 | Helped |
| use WGDL rather than NGRAMCNN | graph classification · MUTAG | accuracy: 94.99±5.63 vs 94.68±2.63 | No clear effect |
| use WGDL rather than P-WL-UC | graph classification · NCI1 | accuracy: 85.62 ±0.27 vs 80.30±2.45 | Hurt |
Closest papers by meaning
- Wasserstein Embedding for Graph Learning (ICLR 2021 · similarity 0.90)
- Wasserstein Weisfeiler-Lehman Graph Kernels (NeurIPS 2019 · similarity 0.88)
- Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching (NeurIPS 2019 · similarity 0.88)
- Improving Distinguishability of Class for Graph Neural Networks (AAAI 2024 · similarity 0.86)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.86)
- Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive 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.