AI Paper Atlas

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

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add feature reconstruction loss (ablation)CG-MAE · MDASACC (%): 31.46 -> 49.09Improved
add feature reconstruction loss (ablation)CG-MAE · XuZhouACC (%): 71.05 -> 83.42Improved
add clustering-guided feature masking (ablation)CG-MAE · XuZhouACC (%): 78.68 -> 83.42Improved
add clustering-guided feature masking (ablation)CG-MAE · TrentoACC (%): 93.52 -> 95.59Improved
add homogeneous edge reconstruction loss (ablation)CG-MAE · MDASACC (%): 48.36 -> 49.09Improved
add homogeneous edge reconstruction loss (ablation)CG-MAE · TrentoACC (%): 94.96 -> 95.59Improved
add edge reconstruction loss (ablation)CG-MAE · SalinasNMI (%): 83.28 -> 83.27No clear effect
add dual self-adaptive KL loss (ablation)CG-MAE · SalinasACC (%): 81.39 -> 82.74Improved
add dual self-adaptive KL loss (ablation)CG-MAE · MDASACC (%): 48.13 -> 49.09Improved
use CG-MAE instead of SAMVGCSAMVGC · TrentoNMI (%): 93.36 -> 91.33Hurt
use CG-MAE instead of SAMVGCSAMVGC · SalinasACC (%): 67.72 -> 82.74Improved
increase neighborhood size k or number of superpixels M (ablation)CG-MAE · XuZhouACCMixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy