AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

PAGE: A Unified Approach for Federated Graph Unlearning

Yuming Ai, Xunkai Li, Jiaqi Chao, Bowen Fan, Zhengyu Wu, Yinlin Zhu, Rong-Hua Li, Guoren Wang

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph 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
use PAGE instead of the best baseline for client unlearningfederated graph unlearning · 8 datasets, client unlearningaccuracy: +5.08% average over SOTAImproved
use PAGE instead of the best baseline for meta unlearningfederated graph unlearning · 8 datasets, meta unlearningaccuracy: +1.50% average over SOTAImproved
scale up graph size (small to large datasets)PAGE client unlearning · Photo vs ogbn-arxivaccuracy gain over SOTA: 2.13% on Photo vs 11.84% on ogbn-arxivImproved
add the influenced unlearn component (adversarial graph + negative distillation) to existing graph unlearning methods (ablation)GIF, D2DGN, MEGU, FedLU, FedDM · Cora, meta unlearningprediction performance: +2.82% averageImproved
add the influenced unlearn component to existing graph unlearning methods (ablation)GIF, D2DGN, MEGU, FedLU, FedDM · Cora, meta unlearningunlearning performance (AUC-ROC): +4.64% averageImproved
add the influenced unlearn component to existing graph unlearning methods (ablation)GIF, D2DGN, MEGU, FedLU, FedDM · CS, meta unlearningprediction performance: +4.49%Improved
add the influenced unlearn component to existing graph unlearning methods (ablation)GIF, D2DGN, MEGU, FedLU, FedDM · CS, meta unlearningunlearning performance (AUC-ROC): +7.22%Improved
use PAGE under increasing edge attack ratiometa unlearning on Photo (GAT, SGC) · Photo with poisoned edgesaccuracy: 2.94% to 8.62% higher than SOTAImproved
use PAGE instead of FedLU for edge and feature meta unlearningPhysics and Computers, Metis and Metis-Plus splits · Table 2accuracyMixed
raise the client unlearn ratio from 0.1 to 0.9 (ablation)PAGE · Chameleon, Minesweeper (GraphSAGE, louvain)accuracyNo clear effect
use PAGE on small-scale datasets versus baselinesclient unlearning · small datasets (Cora, PubMed)accuracyNo clear effect

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