AI Paper Atlas

Research map / Graph learning / GNN architectures

Attribute-guided Dynamic Prompt Learning for Graph Neural Networks

Zhuomin Liang, Liang Bai, Xian Yang

AAAI 2026 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 0 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 prompt adaptation module (dynamic prompts) to fixed prompts (ablation)AttrPrompt · Cora, add 50% edgesaccuracy (%): 77.49 -> 77.90Improved
add prompt adaptation module to fixed prompts (ablation)AttrPrompt · A-Comp., add 75% edgesaccuracy (%): 72.65 -> 73.72Improved
add prompt adaptation module to fixed prompts (ablation)AttrPrompt · A-Comp., delete 50% edgesaccuracy (%): 79.98 -> 81.10Improved
add prompt adaptation module to fixed prompts (ablation)AttrPrompt · Citeseer, delete 50% edgesaccuracy (%): 70.71 -> 71.64Improved
add mutual information loss to dynamic prompts (ablation)AttrPrompt · A-Comp., add 75% edgesaccuracy (%): 73.72 -> 74.16Improved
add mutual information loss to dynamic prompts (ablation)AttrPrompt · Cora, delete 50% edgesaccuracy (%): 78.73 -> 78.92Improved
add mutual information loss to dynamic prompts (ablation)AttrPrompt · A-Photo, add 75% edgesaccuracy (%): 77.72 -> 77.73No clear effect
use attribute-guided prompts on frozen GCNGCN · A-Photo, add 75% edgesaccuracy (%): 67.28 -> 77.73Improved
use attribute-guided prompts on frozen GCNGCN · Cora, add 50% edgesaccuracy (%): 76.36 -> 78.20Improved
use attribute-guided prompts on frozen GCNGCN · A-Comp., add 50% edgesaccuracy (%): 69.76 -> 78.04Improved
use AttrPrompt instead of GOOD-ATGCN · Cora, add 75% edgesaccuracy (%): 76.32 -> 74.43Hurt
use AttrPrompt instead of CaNetGCN · A-Photo, add 75% edgesaccuracy (%): 79.70 -> 77.73Hurt

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