Research map / Graph learning / Graph self-supervised learning
Deep Graph Clustering via Dual Correlation Reduction
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 |
|---|---|---|---|
| replace DFCN with DCRN's dual correlation reduction approach | DFCN graph-clustering backbone · DBLP, CITE, ACM, AMAP, PUBMED, CORAFULL | ACC: 76.00±0.80 -> 79.66±0.25; 69.50±0.20 -> 70.86±0.18; 90.90±0.20 -> 91.93±0.20; 76.88±0.80 -> 79.94±0.13; 68.89±0.07 -> 69 | Helped |
| add propagation regularization (ablation) | DFCN backbone · DBLP | ACC: 76.00±0.80 -> 77.00±0.41 | Helped |
| add propagation regularization (ablation) | DFCN backbone · CORAFULL | ACC: 37.51±0.81 -> 37.04±0.71 | Hurt |
| add DICR mechanism (ablation) | DFCN backbone · DBLP, CITE, ACM, AMAP, PUBMED, CORAFULL | ACC: 76.00±0.80 -> 79.63±0.27; 69.50±0.20 -> 70.88±0.19; 90.90±0.20 -> 91.91±0.21; 76.88±0.80 -> 79.95±0.04; 68.89±0.07 -> 69 | Helped |
| add propagation regularization and DICR together (ablation) | DFCN backbone · DBLP, CITE, ACM, AMAP, PUBMED, CORAFULL | ACC: 76.00±0.80 -> 79.66±0.25; 69.50±0.20 -> 70.86±0.18; 90.90±0.20 -> 91.93±0.20; 76.88±0.80 -> 79.94±0.13; 68.89±0.07 -> 69 | Helped |
| use feature-level correlation reduction alone instead of both correlation levels (ablation) | DFCN backbone · DBLP and CORAFULL | clustering performance | Mixed |
| use sample-level correlation reduction alone (ablation) | DFCN backbone · six benchmark datasets | clustering performance: 3.60% accuracy improvement on DBLP | Helped |
| vary hyper-parameter K (ablation) | DCRN · six benchmark datasets | ACC | No clear effect |
Closest papers by meaning
- DGCBench: A Deep Graph Clustering Benchmark (NeurIPS 2025 · similarity 0.90)
- Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation (ICML 2025 · similarity 0.87)
- DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (AAAI 2024 · similarity 0.87)
- Attribute-Missing Graph Clustering Network (AAAI 2024 · similarity 0.87)
- Deep Multi-modal Graph Clustering via Graph Transformer Network (AAAI 2025 · similarity 0.86)
- Deep Temporal Graph Clustering (ICLR 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.