AI Paper Atlas

Research map / Graph learning / GNN architectures

Reliable and Compact Graph Fine-Tuning via Graph Sparse Prompting

Bo Jiang, Hao Wu, Beibei Wang, Jin Tang, Bin Luo

TPAMI 2026 · Graph learning › GNN architectures · approach: GNN generalization theory · 2 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 l1 sparsity on the prompt vector (GSFP)GPF · Cora 1-shot node classification (GraphMAE)accuracy: 35.15 -> 38.56Improved
add l2,1 row sparsity on the prompt matrix (GSmFP)GPF-plus · Photo 1-shot node classification (GraphMAE)accuracy: 46.41 -> 49.99Improved
add l1 sparsity on the prompt vector (GSFP)GPF · Ogbn-arxiv 1-shot node classification (GraphMAE)accuracy: 9.11 -> 10.81Improved
add l1 sparsity on the prompt vector (GSFP)GPF · PubMed 1-shot node classification (GraphCL)accuracy: 48.25 -> 53.56Improved
add l1 sparsity on the prompt vector (GSFP)GPF · Cora 1-shot node classification (GraphCL)accuracy: 33.24 -> 33.20No clear effect
add l2,1 row sparsity on the prompt matrix (GSmFP)GPF-plus · CiteSeer 1-shot node classification (GraphMAE)accuracy: 31.05 -> 33.61Improved
add l2,1 row sparsity on the prompt matrix (GSmFP)GPF-plus · IMDB-B 1-shot graph classification (GraphCL)accuracy: 61.74 -> 65.05Improved
add l1 sparsity on the prompt vector (GSFP)GPF · IMDB-M 1-shot graph classification (GraphCL)accuracy: 37.77 -> 38.19No clear effect
add l1 sparsity on the prompt vector (GSFP)GPF · Cora with GAT backbone (GraphMAE)accuracy: 35.18 -> 38.79Improved
add l2,1 row sparsity on the prompt matrix (GSmFP)GPF-plus · Photo with GraphSAGE backbone (GraphMAE)accuracy: 45.55 -> 48.08Improved
increase sparsity penalty lambda beyond a moderate range (ablation)GSFP and GSmFP · node classification datasetsaccuracyHurt
use moderate sparsity penalty lambda over lambda=0 (GPF) (ablation)GSFP and GSmFP · node classification datasetsaccuracyImproved

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