Research map / Graph learning / Graph algorithms and clustering
From One to All: Learning to Match Heterogeneous and Partially Overlapped Graphs
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 learned node embeddings to partial GW matching (ablation) | FOTA · Homogeneous graphs; PPI Yeast, ρ=0.6 | F1: 41.7$\pm$0.0 -> 51.6$\pm$0.2 | Helped |
| Add learned node embeddings to partial GW matching (ablation) | FOTA · Heterogeneous graphs; PubMed, ρ=0.8 | F1: 49.9$\pm$0.0 -> 53.1$\pm$0.0 | Helped |
| Use only partial Wasserstein discrepancy instead of the combined partial GW and Wasserstein objective (ablation) | FOTA · Homogeneous graphs; Arenas Email, ρ=0.6 | F1: 17.3$\pm$0.3 -> 1.0$\pm$0.4 | Hurt |
| Use only partial Wasserstein discrepancy instead of the combined objective (ablation) | FOTA · Heterogeneous graphs; Movie, ρ=1.0 | F1: 93.7$\pm$0.3 -> 17.3$\pm$3.6 | Hurt |
| Use partial OT with a searched transport mass rather than full matching | FOTA · Homogeneous graphs with partial overlap | F1 | Helped |
| Decompose matching by node type and use previously matched nodes as seeds | FOTA · Heterogeneous graphs | type mismatch ratio: 0.0$\pm$0.0 | Helped |
Closest papers by meaning
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.91)
- Gromov-Wasserstein Learning for Graph Matching and Node Embedding (ICML 2019 · similarity 0.90)
- Learning Combinatorial Solver for Graph Matching (CVPR 2020 · similarity 0.89)
- M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering (ICLR 2024 · similarity 0.87)
- Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport (AAAI 2025 · similarity 0.86)
- Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval (NeurIPS 2024 · 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.