AI Paper Atlas

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

Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting Without Disclosure

Hanlin Gu, Hong Xi Tae, Lixin Fan, Chee Seng Chan

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 4 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 few-shot manifold mixup unlearning instead of Fisher forgettinglabel unlearning in VFL · CIFAR10 (ResNet18)accuracy on D^r (%): 54.4 -> 89.29Improved
use manifold mixup unlearning instead of Boundary Unlearninglabel unlearning in VFL · ModelNet (ResNet18)accuracy on D^r (%): 24.07 -> 87.69Improved
use manifold mixup unlearning instead of SSDlabel unlearning in VFL · Brain Tumor MRI (ResNet18)accuracy on D^r (%): 85.93 -> 93.79Improved
manifold mixup unlearning versus retraininglabel unlearning in VFL · MNIST (ResNet18)accuracy on D^r (%): 99.33 -> 99.05Hurt
add manifold mixup to few-shot gradient ascent (GA-S) (ablation)few-shot gradient ascent · CIFAR10 (ResNet18)unlearning of y^u and D^r accuracyMixed
add remained accuracy recovery module (ablation)GA-S + manifold mixup · CIFAR10 (ResNet18)D^r accuracyImproved
few-shot gradient ascent without mixup (GA-S) instead of all-data GA-A (ablation)gradient ascent · CIFAR10 (ResNet18)unlearning of y^uHurt
vary mixup coefficient lambda (0.25 vs 0.5) (ablation)manifold mixup unlearning · CIFAR10 (ResNet18)unlearning effectivenessNo clear effect
increase number of passive parties (ablation)manifold mixup unlearning · CIFAR10 (ResNet18)D^r, y^u accuracy and ASRNo clear effect
use manifold mixup unlearning instead of retraining for process privacylabel unlearning in VFL · CIFAR10/100 (ResNet18)membership leakage rate (%): 100 -> 14.38Improved
manifold mixup unlearning vs SSD on ASRlabel unlearning in VFL · ModelNet and Brain MRI (ResNet18)ASRMixed
manifold mixup unlearning vs Amnesiac on two-label ASRlabel unlearning in VFL · CIFAR10 two-label (ResNet18)ASR (%): 1.84 vs 24.21Hurt

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