Research map / Graph learning / Graph algorithms and clustering
A Unified Framework for Optimization-Based Graph Coarsening
Manoj Kumar, Anurag Sharma, Sandeep Kumar
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 FGC (joint graph and feature coarsening) instead of the best adjacency-only baseline | graph coarsening · Cora (r=0.5) | REE: 0.51 -> 0.051 | Improved |
| use FGC (joint graph and feature coarsening) instead of the best adjacency-only baseline | graph coarsening · Citeseer (r=0.5) | REE: 0.54 -> 0.04 | Improved |
| use FGC (joint graph and feature coarsening) instead of the best adjacency-only baseline | graph coarsening · Polblogs (r=0.5) | REE: 0.67 -> 0.007 | Improved |
| use FGC (joint graph and feature coarsening) instead of the best adjacency-only baseline | graph coarsening · ACM (r=0.5) | REE: 0.40 -> 0.034 | Improved |
| use FGC instead of LVN | graph coarsening · Cora (r=0.5) | hyperbolic error: 2.29 -> 1.18 | Improved |
| lower the coarsening ratio r from 0.7 to 0.3 | FGC · Cora | REE: 0.04 -> 0.058 | Hurt |
Closest papers by meaning
- Featured Graph Coarsening with Similarity Guarantees (ICML 2023 · similarity 0.95)
- Graph Coarsening with Neural Networks (ICLR 2021 · similarity 0.90)
- Taxonomy of reduction matrices for Graph Coarsening (NeurIPS 2025 · similarity 0.90)
- Graph Coarsening with Message-Passing Guarantees (NeurIPS 2024 · similarity 0.88)
- UGC: Universal Graph Coarsening (NeurIPS 2024 · similarity 0.87)
- Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training (AAAI 2025 · similarity 0.87)
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.
