Research map / Graph learning / Graph self-supervised learning
Graph Contrastive Clustering
Huasong Zhong, Jianlong Wu, Chong Chen, Jianqiang Huang, Minghua Deng, Liqiang Nie, Zhouchen Lin, Xian-Sheng Hua
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 |
|---|---|---|---|
| add representation graph contrastive loss (ablation) | GCC without graph contrastive · CIFAR-10 | ACC: 0.752 -> 0.809 | Improved |
| add assignment graph contrastive loss (ablation) | GCC without graph contrastive · CIFAR-10 | ACC: 0.752 -> 0.825 | Improved |
| add both RGC and AGC (ablation) | GCC without graph contrastive · CIFAR-10 | ACC: 0.752 -> 0.856 | Improved |
| add both RGC and AGC (ablation) | GCC without graph contrastive · CIFAR-100 | ACC: 0.438 -> 0.472 | Improved |
| add both RGC and AGC (ablation) | GCC without graph contrastive · ImageNet-10 | ACC: 0.878 -> 0.901 | Improved |
| add cluster regularization loss (ablation) | GCC w/o CR · CIFAR-10 | ACC: 0.680 -> 0.856 | Improved |
| add cluster regularization loss (ablation) | GCC w/o CR · CIFAR-100 | ACC: 0.348 -> 0.472 | Improved |
| add cluster regularization loss (ablation) | GCC w/o CR · ImageNet-10 | ACC: 0.828 -> 0.901 | Improved |
| apply SCAN self-labeling fine-tuning to GCC | GCC · CIFAR-10 | ACC: 0.856 -> 0.901 | Improved |
| use GCC instead of SCAN, with self-labeling | SCAN* · CIFAR-100 | ACC: 0.507 -> 0.523 | Improved |
| use graph contrastive features instead of simCLR (spectral clustering) | simCLR + SC · CIFAR-10 | ACC: 0.660 -> 0.746 | Improved |
| use graph contrastive features instead of simCLR (K-means) | simCLR + K-means · CIFAR-100 | ACC: 0.380 -> 0.420 | Improved |
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 0.91)
- GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling (AAAI 2025 · similarity 0.89)
- Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering (NeurIPS 2025 · similarity 0.89)
- Multi-View Graph Clustering via Node-Guided Contrastive Encoding (ICML 2025 · similarity 0.88)
- Contrastive Learning is Spectral Clustering on Similarity Graph (ICLR 2024 · similarity 0.88)
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.
