Research map / Graph learning / Graph self-supervised learning
PAGPL: Privacy-Aware Graph Prompt Learning Scheme via Adaptive Perturbation-Estimated Topology Recovery
Ju Jia, Jiansen Song, Jingxuan Yu, Jiabao Guo, Xiaoshuang Jia, Di Wu, Yali Yuan, Guang Cheng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add adaptive Bayesian graph reconstruction before prompting (ablation) | PAGPL · node-level and graph-level tasks (eps=5.0) | accuracy, F1, AUC | Improved |
| add privacy-aware noise-residual prompt module (ablation) | PAGPL · node-level and graph-level tasks (eps=5.0) | accuracy, F1, AUC | Improved |
| add joint optimization with multi-view privacy consistency (ablation) | PAGPL · node-level and graph-level tasks (eps=5.0) | accuracy, F1, AUC | Improved |
| increase shots from 1 to 10 to 50 | PAGPL · Cora, CiteSeer, PubMed, DD (eps=6.0) | accuracy | Improved |
| swap prompt method to PAGPL on GCN encoder | ProG · Cora (5-shot, eps=10) | accuracy: 42.35 -> 56.81 | Improved |
| swap prompt encoder among GCN, GAT, GraphSAGE | PAGPL · Cora (5-shot, eps=10) | accuracy: 56.81 / 55.51 / 52.74 | No clear effect |
Closest papers by meaning
- On provable privacy vulnerabilities of graph representations (NeurIPS 2024 · similarity 0.87)
- Going Deeper into Locally Differentially Private Graph Neural Networks (ICML 2025 · similarity 0.87)
- Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding (AAAI 2024 · similarity 0.86)
- One Prompt Fits All: Universal Graph Adaptation for Pretrained Models (NeurIPS 2025 · similarity 0.85)
- FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks (ICML 2025 · similarity 0.85)
- Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks (AAAI 2024 · similarity 0.84)
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.
