AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Dynamic Deep Graph Learning for Incomplete Multi-View Clustering with Masked Graph Reconstruction Loss

Zhenghao Zhang, Jun Xie, Xingchen Chen, Tao Yu, Hongzhu Yi, Kaixin Xu, Yuanxiang Wang, Tianyu Zong, Xinming Wang, Jiahuan Chen, Guoqing Chao, Feng Chen and 2 more

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 6 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 masked graph reconstruction loss (ablation)DGIMVCM · 100Leaves, missing rate 0.5ACC: 0.704 -> 0.812Improved
add GCN embedding layer with graph contrastive loss (ablation)DGIMVCM · 100Leaves, missing rate 0.5ACC: 0.529 -> 0.812Improved
add self-supervised pseudo-label clustering module (ablation)DGIMVCM · 100Leaves, missing rate 0.5ACC: 0.806 -> 0.812Improved
use masked top-k graph reconstruction loss instead of traditional MSE loss (ablation)DGIMVCM · Scene-15, missing rate 0.1ACC: 0.479 -> 0.505Improved
use masked loss instead of traditional loss (ablation)DGIMVCM · Scene-15, missing rate 0.3ACC: 0.469 vs 0.470No clear effect
use masked loss instead of traditional loss (ablation)DGIMVCM · Scene-15, missing rate 0.7ACC: 0.403 -> 0.426Improved
vary loss weights alpha and beta from 1e-3 to 1e2 (ablation)DGIMVCM · Landuse-21, missing rate 0.5clustering performanceNo clear effect

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