AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Graph-Oriented Instruction Tuning of Large Language Models for Generic Graph Mining

Yanchao Tan, Hang Lv, Pengxiang Zhan, Shiping Wang, Carl Yang

TPAMI 2025 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 26 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 CoT-based instructions to NC instruction package (ablation)MuseGraph (LLaMA3-8B) · IMDBMicro-F1: 71.23 -> 73.03Improved
add CoT-based instructions to NC instruction package (ablation)MuseGraph (LLaMA3-8B) · IMDBMacro-F1: 70.62 -> 71.45Improved
raise LP CoT package allocation from 1:1 to 3:1 with NC (ablation)MuseGraph (LLaMA3-8B) · IMDBMicro-F1: 72.81 -> 74.86Improved
diversify instruction packages across multiple tasks and datasets (full MuseGraph) (ablation)MuseGraph (LLaMA3-8B) · IMDBMicro-F1: 74.86 -> 76.57Improved
integrate all one-hop neighbors versus central node attributes only (ablation)MuseGraph · IMDBMacro-F1: up to 13.34%Improved
extend neighborhood to two-hop or three-hop without sampling (ablation)MuseGraph · IMDBMicro-F1Hurt
one-hop neighbors plus random walks with node-energy selection versus plain multi-hop neighbors (ablation)MuseGraph · IMDBMicro-F1Improved
use LLaMA3-8B instead of other foundation models (ablation)MuseGraph · multiple tasksaccuracy and BLEU-4: 0.96% in Macro-F1 on IMDB to 15.61% in BLEU-4Improved
graph-aware instruction tuning of LLaMA3-8BLLaMA3-8B · FreebaseMacro-F1: 3.76 -> 59.62Improved
graph-aware instruction tuning of LLaMA3-8BLLaMA3-8B · WebNLG (500 instances)BLEU-4: 36.54 -> 36.83Improved
MuseGraph versus TAPE (GCN) on homogeneous NCMuseGraph (LLaMA3-8B) · CoraMicro-F1: 88.19 vs 86.83Hurt
MuseGraph versus GNN baselines on link predictionMuseGraph · link predictionAUC: 17.54%Improved

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