AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks

Dongxiao He, Wenxuan Sun, Yongqi Huang, Jitao Zhao, Di Jin

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Mixture and distillation for domain shift · 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 both contrastive alignment loss and topology-consistent fusion loss (versus merging branches without loss) (ablation)GP2F · 1-shot node classification (GRACE)accuracyImproved
add contrastive alignment loss L_ctr (ablation)GP2F · 1-shot node classification (GRACE)accuracyImproved
add topology-consistent fusion loss L_fus (ablation)GP2F · 1-shot node classification (GRACE)accuracyImproved
add frozen pre-trained branch to the adapted (prompt) branch (ablation)GP2F · 1-shot node classification (GRACE)accuracyImproved
larger adapter projection dimension r (ablation)GP2F · 1-shot node classification (GRACE)accuracyMixed
use GP2F instead of best baseline GPL methodGP2F · 1-shot node classification, 7 datasetsaccuracy: improves the performance by 1.66% on averageImproved
use GP2F instead of best baseline on CiteSeer and CSGP2F · 1-shot node classificationaccuracy: 3.45% and 3.49%Improved
use GP2F instead of best baseline on BZR and COX2GP2F · 50-shot graph classificationAUC: 1.83% and 3.02%Improved
use linear probing instead of graph prompt learningGRACE/DGI/GraphMAE · 1-shot node classificationaccuracyNo clear effect
pre-train on multiple domains (graph foundation models) instead of single domainGCOPE/MDGPT/MDGFM · 1-shot cross-domain node classificationaccuracyHurt
use GP2F with DGI or GraphMAE pre-training instead of GRACEGP2F · 1-shot node classificationaccuracyNo 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