Research map / Graph learning / Graph algorithms and clustering
Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
Check 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 GENN-A* instead of Hungarian-A* | GED solving · AIDS | averaged time (sec): 29.915 -> 13.323 | Helped |
| Use GENN-A* instead of Hungarian-A* | GED solving · LINUX | averaged time (sec): 2.332 -> 2.177 | Helped |
| Use GENN-A* instead of Hungarian-A* | GED solving · Willow-Cars | averaged time (sec): 188.234 -> 78.481 | Helped |
| Use GENN-A* instead of Beam Search | GED solving · AIDS | ρ: 0.609 -> 0.959 | Helped |
| Use GENN-A* instead of Beam Search | GED solving · LINUX | p@10: 0.973 -> 0.962 | Hurt |
| Use GENN-A* instead of Beam Search | GED solving · Willow-Cars | ρ: 0.815 -> 0.928 | Helped |
| Use GENN-A* instead of Beam Search | GED solving · AIDS | mse (×10⁻³): 12.090 -> 0.635 | Helped |
| Use GENN-A* instead of Beam Search | GED solving · LINUX | mse (×10⁻³): 9.268 -> 0.324 | Helped |
| Use GENN-A* instead of Beam Search | GED solving · Willow-Cars | mse (×10⁻³): 1.820 -> 0.599 | Helped |
| Reuse cached last-layer node embeddings rather than recomputing the full graph (ablation) | GENN dynamic embedding · LINUX | time to predict h(p) (msec): 2.329 -> 0.417 | Helped |
| Use exact dynamic embedding with intermediate caching and neighborhood updates (ablation) | GENN dynamic embedding · LINUX | time to predict h(p) (msec): 0.417 -> 3.145 | Hurt |
Closest papers by meaning
- Graph Edit Distance with General Costs Using Neural Set Divergence (NeurIPS 2024 · similarity 0.92)
- Position: Graph Matching Systems Deserve Better Benchmarks (ICML 2025 · similarity 0.91)
- Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN (NeurIPS 2025 · similarity 0.89)
- GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code (ICML 2025 · similarity 0.88)
- Fully Dynamic Embedding into $\ell_p$ Spaces (ICML 2025 · similarity 0.86)
- GraSP: Simple Yet Effective Graph Similarity Predictions (AAAI 2025 · 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.