AI Paper Atlas

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

FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning

Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 0 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
share attribution-masked, noised features with the server (FedXDS-LRP)FedAvg · CIFAR-10 K=100, alpha=0.1top-1 accuracy: 60.94 -> 80.29Improved
add FedXDS to FedDynFedDyn · CIFAR-10 K=10top-1 accuracy: 70.62 -> 84.20Improved
use LRP rather than Gradient/SmoothGrad/IG as the attribution method (ablation)FedXDS · CIFAR-10 K=10, alpha=0.1, s=70top-1 accuracy: 75.89 (IG) -> 83.46Improved
increase sparsification level from 60 to 85 (ablation)FedXDS-LRP · CIFAR-10 K=10, alpha=0.1top-1 accuracy: 84.74 -> 81.88Hurt
increase privacy budget epsilon from 5 to 20 (less noise) (ablation)FedXDS-LRP · CIFAR-10 K=10, alpha=0.1top-1 accuracy: 80.06 -> 83.46Improved
set knowledge weight lambda to 0.5 instead of 0.0 or 1.0 (ablation)FedXDS · CIFAR-10top-1 accuracy: 72.90 (lambda=0) and 61.18 (lambda=1.0) -> 83.46Improved
increase warmup rounds (ablation)FedXDS · CIFAR-10, CIFAR-100, Tiny-ImageNetaccuracyNo clear effect
apply attribution masking before adding noise (ablation)DP feature sharing · membership inference and feature inversionattack successImproved
FedXLRP versus FedFed on CIFAR-100 K=10 alpha=0.05 and Tiny-ImageNet K=100 alpha=0.1FedXLRP · CIFAR-100 / Tiny-ImageNettop-1 accuracy: 52.07 vs 52.27; 33.18 vs 34.89Mixed

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