AI Paper Atlas

Research map / Graph learning / GNN architectures

Shared Growth of Graph Neural Networks via Prompted Free-Direction Knowledge Distillation

Kaituo Feng, Yikun Miao, Changsheng Li, Ye Yuan, Guoren Wang

TPAMI 2025 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 9 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 the RL knowledge judge (vs distilling every node both ways) (ablation)FreeKD with GCN-GCN · CoraMicro-F1: 85.83 -> 86.53Improved
use RL agent instead of cross-entropy-loss heuristic for direction (ablation)FreeKD with GCN-GCN · ChameleonMicro-F1: 35.77 -> 37.48Improved
use RL agent instead of cross-entropy-loss heuristic for direction (ablation)FreeKD with GCN-GCN · CoraMicro-F1: 85.89 -> 86.53Improved
add structure-level actions (ablation)FreeKD with GCN-GCN · CoraMicro-F1: 86.13 -> 86.53Improved
select agent-selected neighborhood instead of all neighbors (ablation)FreeKD with GCN-GCN · ChameleonMicro-F1: 36.54 -> 37.48Improved
add structure-level distillation to node-level distillation (ablation)FreeKD with GCN-GCN · ChameleonMicro-F1: 36.18 -> 37.48Improved
add information preservation loss to FreeKD-Prompt (ablation)FreeKD-Prompt with GCN-GCN · ChameleonMicro-F1: 37.91 -> 40.04Improved
add diversity loss to FreeKD-Prompt (ablation)FreeKD-Prompt with GCN-GCN · ChameleonMicro-F1: 39.30 -> 40.04Improved
add information preservation loss to FreeKD-Prompt (ablation)FreeKD-Prompt with GCN-GCN · CoraMicro-F1: 86.74 -> 87.33Improved
add FreeKD mutual distillation between two GCNsGCN · ChameleonMicro-F1: 33.09 -> 37.48Improved
add prompt-based augmentation on top of FreeKDFreeKD with GCN-GCN · TexasMicro-F1: 60.00 -> 65.41Improved
add FreeKD-Prompt to GraphSAGEGraphSAGE · PPIMicro-F1: 69.28 -> 72.95Improved

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