Research map / Graph learning / Graph algorithms and clustering
Clustering with Self-Learned Graph Regression
Lai Wei, Jin Liu
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 |
|---|---|---|---|
| use self-learned graph regularizer instead of k-nn graph regularizer (ablation) | SGR · COIL100 | ACC (%): 65.28 -> 82.79 | Improved |
| use self-learned graph regularizer instead of k-nn graph regularizer (ablation) | SGR · JAFFE | ACC (%): 98.12 -> 99.53 | Improved |
| use self-learned graph regularizer instead of k-nn graph regularizer (ablation) | SGR · MNIST | ACC (%): 59.22 -> 68.21 | Improved |
| put hard-rank constraint on auxiliary C rather than on S (ablation) | SGR · MNIST | ACC (%): 34.49 -> 68.21 | Improved |
| put hard-rank constraint on auxiliary C rather than on S (ablation) | SGR · COIL20 | ACC (%): 87.36 -> 98.33 | Improved |
| cluster from S instead of C (ablation) | SGR · JAFFE | ACC (%): 92.96 -> 99.53 | Improved |
| cluster from S instead of C (ablation) | SGR · MNIST | NMI (%): 69.04 (C) vs 75.82 (S) | Hurt |
| SGR-S vs strongest baseline SDSGC | SGR · COIL20 | ACC (%): 84.72 -> 98.33 | Improved |
| SGR-S vs strongest baseline SDSGC | SGR · Zoo | ACC (%): 67.33 -> 82.18 | Improved |
| restrict updates to k-nn sparsity pattern (acceleration, k=30 vs n-1) (ablation) | SGR · runtime | running time | Improved |
| vary alpha and beta in grid (ablation) | SGR-S · six datasets | NMI | No clear effect |
| vary neighborhood size k in {20,30,40,50,n-1} (ablation) | SGR · six datasets | NMI | No clear effect |
Closest papers by meaning
- Affinity Clustering: Hierarchical Clustering at Scale (NeurIPS 2017 · similarity 0.90)
- Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective (NeurIPS 2024 · similarity 0.88)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.88)
- Local Graph Clustering with Noisy Labels (ICLR 2024 · similarity 0.87)
- Every Node Is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering (AAAI 2024 · similarity 0.87)
- DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (AAAI 2024 · 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.
