AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Low-Rank Few-Shot Node Classification by Node-Level Graph Diffusion

Yancheng Wang, Chengshuai Zhao, Dongfang Sun, huan liu, Yingzhen Yang

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning

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 LR-FGDM to COLACOLA · Coauthor-CS 5-way 5-shotaccuracy (%): 87.54 -> 89.83Improved
add LRA layer on top of LR-FGDMCOLA (LR-FGDM) · CoraFull 5-way 5-shotaccuracy (%): 89.66 -> 90.32Improved
add LR-FGDM to COSMICCOSMIC · CoraFull 2-way 5-shotaccuracy (%): 94.51 -> 96.74Improved
add low-rank regularization (ablation)COLA (LR-FGDM) · CoraFull 5-way 5-shotaccuracy (%): 88.74 -> 89.66Improved
add low-rank regularization (ablation)COLA (LR-FGDM) · ogbn-arxiv 5-way 5-shotaccuracy (%): 68.60 -> 69.63Improved
add prototypical regularization (ablation)COLA (LR-FGDM) · Coauthor-CS 5-way 5-shotaccuracy (%): 89.02 -> 89.83Improved
add prototypical regularization (ablation)COLA (LR-FGDM) · DBLP 5-way 5-shotaccuracy (%): 88.64 -> 89.51Improved
add both regularizers (augmentation alone is already slightly helpful) (ablation)COLA (LR-FGDM) · ogbn-arxiv 5-way 5-shotaccuracy (%): 67.91 -> 69.63Improved
use hierarchical edge reconstruction instead of BLND (ablation)LR-FGDM · ogbn-arxiv 5-way 5-shotaccuracy (%): 68.47 -> 69.63Improved
use hierarchical edge reconstruction instead of regular GAE decoder (ablation)HGAE · ogbn-arxiv training timeseconds: 1690 -> 301Improved
use hierarchical edge reconstruction for generation (ablation)FGDM · ogbn-arxiv generation times/sample: 0.426 -> 0.130Improved
add LR-FGDM synthetic support nodes instead of SNS (GAN)COLA · CoraFull 5-way 5-shotaccuracy (%): 88.49 -> 89.66Improved

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