AI Paper Atlas

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

Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels

Yae Jee Cho, Gauri Joshi, Dimitrios Dimitriadis

ICCV 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 12 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 global-local consistency regularization (lambda_0 > 0 versus 0) (ablation)FedLabel · CIFAR10, CIFAR100, OrganAMNIST, BloodMNISTtest accuracy: approximately 5-9% improvementImproved
use very high confidence threshold beta=0.9 instead of lower values (ablation)FedLabel · CIFAR10, CIFAR100, OrganAMNIST, BloodMNISTtest accuracy: lowering beta below 0.9 improves by at most approximately 17%Hurt
use more local steps tau to obtain the local model (tau=5 is worst) (ablation)FedLabel · CIFAR10 and otherstest accuracyImproved
use variance instead of entropy as confidence measure (ablation)FedLabel · OrganAMNIST, BloodMNISTtest accuracyImproved
use variance instead of entropy as confidence measure (ablation)FedLabel · CIFAR10, CIFAR100test accuracyNo clear effect
add strong augmentation (RandAugment) to pseudo-labeled samples (ablation)FedLabel · CIFAR10test accuracyImproved
lower data heterogeneity (alpha 1 versus 0.1)FedLabel vs baselines · CIFAR10, OrganAMNISTaccuracy gap to baselines: gap smaller by around 11-14%Hurt
increase labeled fraction (50% vs 20% for CIFAR10)FedLabel vs baselines · CIFAR10accuracy gap to baselines: gap 15-24% -> 8-15%Hurt
apply FedLabel with 20% labels on CIFAR100 versus fully labeled FedProxFedLabel · CIFAR100test accuracy: 24.87 -> 18.42Hurt
naively combine FixMatch with FedAvg under limited labelsFedAvg · CIFAR10test accuracy: 28.83 -> 23.99Hurt

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