AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning

Yan Jiang, Ruihong Qiu, Zi Huang

ICML 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Extrapolation and single-sample adaptation · 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 test-time graph complementary learning (use unlabelled test nodes) on top of few-shot prompt tuning (ablation)GFMate · Cornell, 1-shotaccuracy (%): 72.59 -> 79.67Improved
add test-time graph complementary learning (ablation)GFMate · Cora, 1-shotaccuracy (%): 54.57 -> 59.68Improved
use complementary labels instead of pseudo-labels from the last layer for test nodes (ablation)GFMate · Cora, 1-shotaccuracy (%): 18.29 -> 59.68Improved
add pseudo-labelled test nodes to few-shot tuning (ablation)GFMate few-shot tuning · Citeseer, 1-shotaccuracy (%): 52.92 -> 13.79Hurt
increase the fraction of available unlabelled test nodes from 0% to full (ablation)GFMate · Cora, 1-shotaccuracy (%): 54.57 -> 59.68Improved
remove centroid prompt, layer prompt, or TGCL (ablation)GFMate · one-shot and three-shot node classificationaccuracyImproved
plug GFMate into LP+FT pre-trained GCNLP+FT · Cornell, 1-shotaccuracy (%): 23.88 -> 79.67Improved
plug GFMate into SAMGPTSAMGPT · Cornell, 1-shotaccuracy (%): 59.34 -> 76.34Improved
swap GCN backbone for SAGE, GAT or H2GCN (ablation)GFMate · Citeseer / Cora, 1-shotaccuracy (%): 56.25 -> 57.39 (SAGE, Citeseer)No clear effect
reduce task to binary classification (ablation)GFMate vs SAMGPT · Coraaccuracy gain over SAMGPT: 6.85 -> 10.58Improved
pre-train GFM only on bioinformatics-domain graphs instead of all other domains (ablation)GFMate · Citeseer, 1-shotaccuracy (%): 56.25 -> 48.09Hurt
shuffle 50% of test node features (feature shift) (ablation)GFMate · Texas, 1-shotaccuracy (%): 76.63 -> 71.24Hurt

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