AI Paper Atlas

Research map / Graph learning / GNN architectures

DuoKD: Dual Knowledge Distillation from Large Language Models for Robust Graph Neural Networks

Cuiying Huo, Xiaotong Huang, Dongxiao He, Yixuan Du, Wenhuan Lu, Di Jin

AAAI 2026 · Graph learning › GNN architectures · approach: Graph structure learning · 1 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 positive knowledge supervision (ablation)DuoKD · Coraaccuracy: 5.8% drop when removedImproved
add negative knowledge supervision (ablation)DuoKD · ogbn-arxivaccuracyImproved
add rationale (semantic and structural) supervision (ablation)DuoKD · Cora/PubMed/ogbn-arxivaccuracyImproved
use DuoKD with GraphSAGE student instead of GLEM (SAGE)DuoKD · PubMedaccuracy: 89.30 -> 88.05Hurt
use DuoKD instead of LinguGKD (SAGE)DuoKD · Coraaccuracy: 90.91 -> 91.85Improved
use DuoKD instead of LinguGKD (GAT)DuoKD · ogbn-arxivaccuracy: 77.62 -> 80.13Improved
use DuoKD instead of GLEM under 40% structural attackDuoKD · Coraaccuracy: 80.78 -> 84.21Improved
use DuoKD instead of GLEM under 40% attribute corruptionDuoKD · PubMedaccuracy: 83.30 -> 84.90Improved
set rationale filter alpha 0.2-0.4 and threshold tau 0.7-0.9 (ablation)DuoKD · heatmapaccuracyImproved
increase loss weights lambda1-3 to 3.0-4.0 (ablation)DuoKD · 3D plotaccuracyImproved

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