Research map / Graph learning / Graph self-supervised learning
Graph Masked Autoencoder for Multi-view Remote Sensing Data Clustering
Renxiang Guan, Junhong Li, Siwei Wang, Tianrui Liu, Dayu Hu, Miaomiao Li, Xinwang 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 |
|---|---|---|---|
| add feature reconstruction loss (ablation) | CG-MAE · MDAS | ACC (%): 31.46 -> 49.09 | Improved |
| add feature reconstruction loss (ablation) | CG-MAE · XuZhou | ACC (%): 71.05 -> 83.42 | Improved |
| add clustering-guided feature masking (ablation) | CG-MAE · XuZhou | ACC (%): 78.68 -> 83.42 | Improved |
| add clustering-guided feature masking (ablation) | CG-MAE · Trento | ACC (%): 93.52 -> 95.59 | Improved |
| add homogeneous edge reconstruction loss (ablation) | CG-MAE · MDAS | ACC (%): 48.36 -> 49.09 | Improved |
| add homogeneous edge reconstruction loss (ablation) | CG-MAE · Trento | ACC (%): 94.96 -> 95.59 | Improved |
| add edge reconstruction loss (ablation) | CG-MAE · Salinas | NMI (%): 83.28 -> 83.27 | No clear effect |
| add dual self-adaptive KL loss (ablation) | CG-MAE · Salinas | ACC (%): 81.39 -> 82.74 | Improved |
| add dual self-adaptive KL loss (ablation) | CG-MAE · MDAS | ACC (%): 48.13 -> 49.09 | Improved |
| use CG-MAE instead of SAMVGC | SAMVGC · Trento | NMI (%): 93.36 -> 91.33 | Hurt |
| use CG-MAE instead of SAMVGC | SAMVGC · Salinas | ACC (%): 67.72 -> 82.74 | Improved |
| increase neighborhood size k or number of superpixels M (ablation) | CG-MAE · XuZhou | ACC | Mixed |
Closest papers by meaning
- Structure-Adaptive Multi-View Graph Clustering for Remote Sensing Data (AAAI 2025 · similarity 0.90)
- R-MAE: Regions Meet Masked Autoencoders (ICLR 2024 · similarity 0.85)
- Self-Guided Masked Autoencoder (NeurIPS 2024 · similarity 0.85)
- Teacher-guided Edge Discriminator for Personalized Graph Masked Autoencoder (AAAI 2025 · similarity 0.85)
- Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum (ICML 2025 · similarity 0.85)
- Rethinking Graph Masked Autoencoders through Alignment and Uniformity (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.
