Research map / Graph learning / Graph self-supervised learning
Self-Supervised Graph Embedding Clustering
Fangfang Li, Quanxue Gao, Xiaoke Ma, Ming Yang, Cheng Dan Deng
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 self-supervised label-guided manifold clustering (Our-LPP) over best prior one-step LDA method | Un-RTLDA · ORL | ACC: 0.663 -> 0.895 | Improved |
| add self-supervised label-guided manifold clustering (Our-LPP) over best prior baseline | Un-TRLDA · UMIST | ACC: 0.501 -> 0.817 | Improved |
| add self-supervised label-guided manifold clustering (Our-MFA) over best prior baseline | Un-RTLDA · AR | ACC: 0.561 -> 0.601 | Improved |
| use Our-MFA instead of Our-LPP | Our-LPP · USPS | ACC: 0.826 -> 0.782 | Hurt |
| use Our-MFA instead of Our-LPP | Our-LPP · ORL | ACC: 0.895 -> 0.848 | Hurt |
| use Our-MFA instead of Our-LPP | Our-LPP · MSRC | ACC: 0.886 -> 0.929 | Improved |
| add dimensionality reduction before clustering | K-means · benchmark datasets | ACC, NMI, Purity | Improved |
| use one-step dimensionality reduction clustering instead of two-step | two-step PCA/LPP/LDA + K-means · benchmark datasets | ACC, NMI, Purity | Improved |
| use local manifold LPP instead of global linear PCA before K-means | PCA-KM · benchmark datasets | ACC | Improved |
| increase neighbor number k from 2 toward n/c (ablation) | Our-LPP · ORL, MSRC, Yaleface | clustering performance: peaks slightly below n/c then declines | Mixed |
| increase neighbor number k (ablation) | Our-LPP · UMIST | clustering performance: peak at k=2 | Hurt |
| increase reduced dimension (ablation) | Our-LPP · ORL, MSRC, UMIST, Yaleface | clustering performance | Mixed |
Closest papers by meaning
- Unified K-Means Clustering with Label-Guided Manifold Learning (ICML 2025 · similarity 0.91)
- Large Scale Manifold Balanced Clustering (ICML 2026 · similarity 0.90)
- Discriminative Graph Embedding Framework via Label-Free Marginal Fisher Analysis (AAAI 2026 · similarity 0.90)
- Clustering is semidefinitely not that hard: Nonnegative SDP for manifold disentangling (JMLR 2018 · similarity 0.88)
- FC$^{2}$2: Fast Co-Clustering With Small-Scale Similarity Graph and Bipartite Graph Learning (TPAMI 2026 · similarity 0.88)
- Clustering Properties of Self-Supervised Learning (ICML 2025 · 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.
