AI Paper Atlas

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

Influence-Disentangled Federated Training: Learning Models That Are Easy to Unlearn

Canran Xiao, Qianyu Chen, Liwei Hou

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Vertical federated learning

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 shared-subspace routing (r>0) (ablation)IDFT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 1.05 -> 0.78Improved
use influence dimension s larger than 32 (ablation)IDFT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 0.86 -> 0.78Improved
add entanglement shrinkage (lambda>0) (ablation)IDFT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 0.84 -> 0.78Improved
add covariance term to entanglement score (ablation)IDFT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 0.89 -> 0.78Improved
add co-adaptation term to entanglement score (ablation)IDFT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 0.88 -> 0.78Improved
add leakage term to entanglement score (ablation)IDFT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 0.90 -> 0.78Improved
add constrained repair rounds after subtraction (ablation)IDFT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 1.22 -> 0.78Improved
add constrained repair rounds after subtraction (ablation)IDFT · CIFAR10-ResNet18 (client unlearning, label-flipping)MIA: 0.56 -> 0.45Improved
add shared-subspace routing (r>0) (ablation)IDFT · CIFAR10-ResNet18 (client unlearning, label-flipping)MIA: 0.50 -> 0.45Improved
use IDFT instead of NoTNoT · CIFAR-10 (ResNet-18), client-wise unlearning (IID, 10 clients)Avg. Gap: 1.78 -> 0.78Improved
use IDFT instead of NoTNoT · CIFAR-10 (CNN), client-wise unlearning (IID, 10 clients)Avg. Gap: 0.29 -> 0.26Improved
use IDFT instead of FUSEDFUSED · CIFAR100-ResNet18 (client unlearning, label-flipping)MIA: 0.48 -> 0.10Improved

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