AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

Xinran Gu, Kaixuan Huang, Jingzhao Zhang, Longbo Huang

NeurIPS 2021 · Federated learning and privacy › Communication-efficient FL · approach: Local drift correction · 24 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
reuse memorized latest updates of inactive devices (MIFA) instead of averaging only active devices (biased FedAvg)MIFA · non-iid CIFAR-10 / MNIST, small p_minoptimality gap / test accuracyImproved
do not wait for sampled devices (impatient MIFA) versus FedAvg with device samplingMIFA · non-iid MNIST and CIFAR-10convergence speedImproved
MIFA without knowledge of participation probabilities versus FedAvg with importance samplingMIFA · non-iid MNIST and CIFAR-10convergence/test accuracyNo clear effect

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