AI Paper Atlas

Research map / Graph learning / GNN architectures

Deep Graph Reprogramming

Yongcheng Jing, Chongbin Yuan, Li Ju, Yiding Yang, Xinchao Wang, Dacheng Tao

CVPR 2023 · Graph learning › GNN architectures · approach: Graph structure learning · 31 citations (OpenAlex)

Read the paper

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 task-adaptive ReAgg to MetaFPMetaFP reusing a Citeseer-pretrained GNN · Pubmedaccuracy: 0.7790 -> 0.8030Improved
Add task-adaptive ReAgg to MetaFPMetaFP reusing a Citeseer-pretrained GNN · Computersaccuracy: 0.9085 -> 0.9229Improved
Add task-adaptive ReAgg to MetaFPMetaFP reusing a Citeseer-pretrained GNN · Photoaccuracy: 0.8909 -> 0.9213Improved
Add task-adaptive ReAgg to MetaFPMetaFP reusing a Citeseer-pretrained GNN · Coraaccuracy: 0.8335 -> 0.8312Hurt
Add MetaFP feature padding rather than vanilla reuseFrozen GNN reused across graph classification and regression tasks · QM7bMAE: 24.18 -> 2.3093Improved
Add MetaFP feature padding rather than vanilla reuseFrozen GNN reused across graph classification and regression tasks · PROTEINSaccuracy: 0.3304 -> 0.6071Improved
Add MetaGP meta-graph padding rather than vanilla reuseGNN pretrained on ogbg-molbace · ogbn-molbbbpROC-AUC: 0.5136 -> 0.6691Improved
Add MetaGP meta-graph padding rather than vanilla reuseGNN pretrained on ogbg-molbace · ogbn-molesolRMSE: 6.950 -> 2.050Improved
Add MetaGP meta-graph padding rather than vanilla reuseDGCNN pretrained on ModelNet40 · ShapeNetaccuracy: 0.1545 -> 0.6090Improved
Use MetaFP padding rather than vanilla reuseGNN pretrained on Citeseer · Coraaccuracy: 0.1571 -> 0.8335Improved
Use random padding placement rather than fixed placement (ablation)MetaFP · Computers → Photoaccuracy: 0.9183; 0.9161; 0.9212; 0.9165No clear effect
Change feature-padding position among front, center, end, and random (ablation)MetaFP · Photo → Pubmedaccuracy: 0.8420; 0.8430; 0.8420; 0.8440No 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