Research map / Graph learning / Graph algorithms and clustering
Adaptive Graph Auto-Encoder for General Data Clustering
Xuelong Li, Hongyuan Zhang, Rui Zhang
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 |
|---|---|---|---|
| make sparsity k grow during graph updates instead of keeping it fixed (ablation) | AdaGAE · COIL20 | ACC: 33.82 -> 93.75 | Improved |
| make sparsity k grow instead of fixed (ablation) | AdaGAE · COIL20 | NMI: 55.46 -> 98.36 | Improved |
| make sparsity k grow instead of fixed (ablation) | AdaGAE · MNIST | ACC: 14.04 -> 92.88 | Improved |
| make sparsity k grow instead of fixed (ablation) | AdaGAE · UMIST | ACC: 32.00 -> 83.48 | Improved |
| make sparsity k grow instead of fixed (ablation) | AdaGAE · PALM | ACC: 91.80 -> 95.25 | Mixed |
| add adaptive graph update (vs fixed graph) (ablation) | AdaGAE · COIL20 | ACC: 92.43 -> 93.75 | Improved |
| add adaptive graph update (vs fixed graph) (ablation) | AdaGAE · 20news | ACC: 38.54 -> 77.28 | Improved |
| add adaptive graph update (vs fixed graph) (ablation) | AdaGAE · USPS | ACC: 67.48 -> 91.96 | Improved |
| add adaptive graph update (vs fixed graph) (ablation) | AdaGAE · Isolet | ACC: 66.15 -> 66.22 | No clear effect |
| add weighted-graph architecture and second loss term to fixed-graph GAE (ablation) | Method-A over GAE-dagger · 20news | ACC: 33.55 -> 38.54 | Improved |
| add weighted-graph architecture and second loss term to fixed-graph GAE (ablation) | Method-A over GAE-dagger · USPS | ACC: 79.40 -> 67.48 | Hurt |
| add full AdaGAE (adaptive graph) over GAE with fixed graph (ablation) | GAE-dagger · MNIST | ACC: 71.07 -> 92.88 | Improved |
Closest papers by meaning
- AW-GBGAE: An Adaptive Weighted Graph Autoencoder Based on Granular-Balls for General Data Clustering (TPAMI 2025 · similarity 0.91)
- HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning (NeurIPS 2024 · similarity 0.87)
- Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation (ICML 2025 · similarity 0.86)
- Generative Graph Pattern Machine (NeurIPS 2025 · similarity 0.86)
- Learning to Reweight for Generalizable Graph Neural Network (AAAI 2024 · similarity 0.86)
- Deep Contrastive Graph Learning with Clustering-Oriented Guidance (AAAI 2024 · similarity 0.85)
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.
