AI Paper Atlas

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

Federated Learning with Label Distribution Skew via Logits Calibration

ICML 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 23 citations (OpenAlex)

Read the paper

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
calibrate local logits with class-count-based pairwise marginsFedAvg-style federated learning · CIFAR10, D(0.05)test accuracy: 44.39±1.63 -> 54.55±1.70Improved
calibrate local logits with class-count-based pairwise marginsFedAvg-style federated learning · CIFAR10, Q(2)test accuracy: 55.91±1.44 -> 61.87±0.94Improved
calibrate local logits with class-count-based pairwise marginsfederated learning · FEMNISTtest accuracy: 87.95±0.92 -> 92.78±0.58Improved
add FedProx regularization to FedLC (ablation)FedLC · CIFAR10, α=5test accuracy: 69.89 -> 71.39Improved
add Scaffold to FedLC (ablation)FedLC · SVHN, α=5test accuracy: 88.19 -> 89.34Improved
increase local epochs from E=1 to E=5 (ablation)FedLC · CIFAR10, β=0.5test accuracy: 70.41 -> 80.25Improved
increase number of clients from m=10 to m=100 (ablation)FedLC · reported test accuracy settingtest accuracy: 70.13 -> 43.81Hurt

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