Research map / Graph learning / Graph self-supervised learning
Cluster-Guided Contrastive Graph Clustering Network
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 cluster-guided positive sample construction instead of same-node positives (ablation) | CCGC · CORA | ACC: 60.03±6.28 -> 73.88±1.20 | Helped |
| Use cluster-guided positive sample construction instead of same-node positives (ablation) | CCGC · CITESEER | ACC: 58.26±6.19 -> 69.84±0.94 | Helped |
| Use reliable negative cluster-center samples instead of treating other samples as negatives (ablation) | CCGC · CORA | ACC: 70.29±0.86 -> 73.88±1.20 | Helped |
| Use reliable negative cluster-center samples instead of treating other samples as negatives (ablation) | CCGC · AMAP | ACC: 73.74±0.82 -> 77.25±0.41 | Helped |
| Use un-shared Siamese encoders instead of edge-drop augmentation (ablation) | CCGC · CORA | ACC: 57.95±4.32 -> 73.88±1.20 | Helped |
| Use un-shared Siamese encoders instead of edge-add augmentation (ablation) | CCGC · CORA | ACC: 57.89±3.16 -> 73.88±1.20 | Helped |
| Use un-shared Siamese encoders instead of graph diffusion augmentation (ablation) | CCGC · CORA | ACC: 59.57±2.95 -> 73.88±1.20 | Helped |
| Use un-shared Siamese encoders instead of feature masking (ablation) | CCGC · CORA | ACC: 67.40±1.76 -> 73.88±1.20 | Helped |
| Use a high-confidence threshold in the range 50% to 70% (ablation) | CCGC · six benchmark datasets | clustering performance | Helped |
| Increase the high-confidence threshold beyond 70% (ablation) | CCGC · six benchmark datasets | clustering performance | Hurt |
| Vary the negative-loss trade-off α (ablation) | CCGC · six benchmark datasets | clustering performance | No clear effect |
| Vary the Laplacian-filter layer number t (ablation) | CCGC · six benchmark datasets | clustering performance | No clear effect |
Closest papers by meaning
- Deep Contrastive Graph Learning with Clustering-Oriented Guidance (AAAI 2024 · similarity 0.93)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.90)
- Multi-View Graph Clustering via Node-Guided Contrastive Encoding (ICML 2025 · similarity 0.89)
- Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view Clustering (AAAI 2025 · similarity 0.88)
- Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering (NeurIPS 2025 · similarity 0.88)
- Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling (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.