Research map / Graph learning / Graph algorithms and clustering
Non-Graph Data Clustering via $\mathcal {O}(n)$ Bipartite Graph Convolution
Hongyuan Zhang, Jiankun Shi, Rui Zhang, Xuelong Li
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 adaptive update of anchors and transition probability (ablation) | AnchorGAE-L2 · MNIST-full | ACC: 0.468 -> 0.833 | Improved |
| add adaptive update of anchors and transition probability (ablation) | AnchorGAE-L2 · MNIST-full | NMI: 0.635 -> 0.773 | Improved |
| add dynamically increasing sparsity k (ablation) | AnchorGAE-L2 · MNIST-full | ACC: 0.289 -> 0.833 | Improved |
| add dynamically increasing sparsity k (ablation) | AnchorGAE-L2 · MNIST-test | ACC: 0.284 -> 0.823 | Improved |
| add dynamically increasing sparsity k (ablation) | AnchorGAE-L2 · SEGMENT | NMI: 0.125 -> 0.613 | Improved |
| use weighted graph instead of KNN graph (ablation) | AnchorGAE-L2 · MNIST-full | ACC: 0.793 -> 0.833 | Improved |
| use weighted graph instead of KNN graph (ablation) | AnchorGAE-L2 · Fashion-MNIST | ACC: 0.533 -> 0.645 | Improved |
| use weighted graph instead of KNN graph (ablation) | AnchorGAE-L2 · ISOLET | ACC: 0.654 -> 0.663 | No clear effect |
| fix anchors (no update) | AnchorGAE-L2 · Fashion-MNIST | ACC: 0.645 -> 0.588 | Hurt |
| use 4-layer instead of 2-layer convolution | AnchorGAE · USPS | ACC: 0.853 -> 0.781 | Hurt |
| use too large initial sparsity k0 | AnchorGAE · SEGMENT and MNIST-test | ACC | Hurt |
Closest papers by meaning
- Do Graph Neural Networks Learn Generalizable Algorithms for Clustering Graphs? (NeurIPS 2026 · similarity 0.91)
- Dink-Net: Neural Clustering on Large Graphs (ICML 2023 · similarity 0.90)
- GC-Flow: A Graph-Based Flow Network for Effective Clustering (ICML 2023 · similarity 0.90)
- Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering (ICML 2023 · similarity 0.90)
- DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (AAAI 2024 · similarity 0.89)
- LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering (ICML 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.
