Research map / Graph learning / Graph algorithms and clustering
Graph Clustering with Graph Neural Networks
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 DMoN instead of MinCutPool | pooling GNN clustering · Cora | NMI: 35.8 -> 48.8 | Helped |
| Use DMoN instead of MinCutPool | pooling GNN clustering · Coauthor Phys | NMI: 48.3 -> 56.7 | Helped |
| Use DMoN instead of MinCutPool | pooling GNN clustering · Citeseer | conductance: 14.1 -> 5.1 | Helped |
| Use DMoN instead of k-means on DGI representations | clustering · Cora | NMI: 52.7 -> 48.8 | Hurt |
| Use DMoN instead of k-means on DGI representations | clustering · Pubmed | NMI: 22.0 -> 29.8 | Helped |
| Use orthogonality-only loss (Ortho) instead of full MinCutPool loss (ablation) | MinCutPool · Cora | NMI: 35.8 -> 38.4 | Mixed |
| Use orthogonality-only loss (Ortho) instead of full MinCutPool loss (ablation) | MinCutPool · Pubmed | NMI: 25.4 -> 20.3 | Hurt |
| Use orthogonality-only loss (Ortho) instead of full MinCutPool loss (ablation) | MinCutPool · Pubmed | conductance: 29.6 -> 57.8 | Hurt |
| Use DMoN with collapse regularization and dropout instead of MinCutPool orthogonality | DMoN · Amazon PC | NMI | Helped |
| Use DMoN instead of SBM (graph only) | clustering · Coauthor Eng | NMI: 33.3 -> 51.8 | Helped |
| Use DMoN instead of NOCD | clustering · Coauthor CS | NMI: 70.5 -> 69.1 | Hurt |
| Use DMoN instead of NOCD | clustering · Amazon PC | NMI: 44.8 -> 49.3 | Helped |
Closest papers by meaning
- Do Graph Neural Networks Learn Generalizable Algorithms for Clustering Graphs? (NeurIPS 2026 · similarity 0.89)
- Machine Learning on Graphs: A Model and Comprehensive Taxonomy (NeurIPS 2022 · similarity 0.88)
- Dink-Net: Neural Clustering on Large Graphs (ICML 2023 · similarity 0.86)
- S3GC: Scalable Self-Supervised Graph Clustering (NeurIPS 2022 · similarity 0.86)
- DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (AAAI 2024 · similarity 0.86)
- Local Graph Clustering with Noisy Labels (ICLR 2024 · similarity 0.84)
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.