AI Paper Atlas

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

Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation

Qi Guo, Zhen Tian, Minghao Yao, Saiyu Qi, Yong Qi, Bingyi Liu

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 10 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 transformation class selection (vs random label) (ablation)FUCRT · CIFAR10 (Non-IID)remaining-class accuracy: 89.24 -> 89.82Improved
add transformation class selection (vs random label) (ablation)FUCRT · FMNIST (Non-IID)remaining-class accuracy: 86.20 -> 90.95Improved
add transformation class selection (vs random label) (ablation)FUCRT · EuroSAT (IID)remaining-class accuracy: 90.19 -> 94.92Improved
add local class-aware contrastive loss (ablation)FUCRT · CIFAR10 (Non-IID)remaining-class accuracy: 20.87 -> 89.82Improved
add local class-aware contrastive loss (ablation)FUCRT · EuroSAT (IID)remaining-class accuracy: 23.10 -> 94.92Improved
add local class-aware contrastive loss (ablation)FUCRT · CIFAR100 (IID)remaining-class accuracy: 75.00 -> 75.25No clear effect
add global class-aware contrastive loss (ablation)FUCRT · CIFAR10 (Non-IID)remaining-class accuracy: 89.76 -> 89.82No clear effect
add global class-aware contrastive loss (ablation)FUCRT · EuroSAT (Non-IID)remaining-class accuracy: 83.41 -> 87.38Improved
add global class-aware contrastive loss (ablation)FUCRT · CIFAR100 (IID)remaining-class F1: 81.35 -> 85.70Improved
use FUCRT instead of fine-tuning on remaining dataFine-tune · FMNIST (IID)unlearning-class accuracy: 91.79 -> 0.00Improved
raise unlearning proportion from 10% to 50%FUCRT · CIFAR10 (IID)FUCRT minus From-scratch remaining accuracy: 90.06 vs 87.99 at 10%; 94.15 vs 95.45 at 50%Hurt

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