AI Paper Atlas

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

FedVeer: Self-Adaptive Skew Estimation for Robust Federated Learning

Yun Xin, Bangqi Pan, Jianfeng Lu, Shuqin Cao, Gang Li, Guanghui Wen

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID 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 self-adaptive kernel density module (k-free neighborhood via max-margin) (ablation)FedVeer · FEMNISTaccuracy: 0.463 -> 0.636Improved
add self-adaptive kernel density module (ablation)FedAvg-style aggregation · FEMNISTaccuracy: 0.377 -> 0.608Improved
add Kalman filter margin stabilization (ablation)FedVeer · FEMNISTaccuracy: 0.608 -> 0.636Improved
add Kalman filter margin stabilization (ablation)FedVeer · CIFAR-10accuracy: 0.588 -> 0.591Improved
add Kalman filter alone without adaptive kernel (ablation)FedAvg-style aggregation · CIFAR-10accuracy: 0.567 -> 0.568No clear effect
vary neighborhood size k from 5 to 15 (ablation)FedVeer · CEKA datasetsaccuracy: audiology 0.545 (k=10) to 0.742 (k=8)Mixed
shrink kernel bandwidth h from x to x/4 (ablation)FedVeer · CIFAR-10accuracy: 0.511 -> 0.238 (k=5)Hurt
shrink kernel bandwidth h from x to x/4 (ablation)FedVeer · Fashion-MNISTaccuracy: 0.739 -> 0.735 (k=5)No clear effect
increase Kalman forgetting factor lambda from 0.3 to 0.9 (ablation)Kalman filter · MNISTerror reduction ratio (x10^-3): 0.071 -> 0.195Improved
decrease Kalman process noise alpha from 0.020 to 0.001 (ablation)Kalman filter · MNISTerror reduction ratio (x10^-3): 0.110 -> 0.351Improved
increase observation noise beta from 0.01 to 0.10 (ablation)Kalman filter · MNISTerror reduction ratio (x10^-3): 0.110 -> 0.300Improved
use FedVeer instead of best baseline TPFL on CEKA averagefederated aggregation · CEKA datasets (34)accuracy: 0.840 -> 0.866Improved

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