AI Paper Atlas

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

Federated Block Coordinate Descent Scheme for Learning Global and Personalized Models

Ruiyuan Wu, Anna Scaglione, Hoi-To Wai, Nurullah Karakoc, Kari Hreinsson, Wing-Kin Ma

AAAI 2021 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 19 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
Allow personalized edge models to deviate from the global model using a quadratic penaltyFedBCD and FedBCD-I · MNIST and CIFAR-10personalized test accuracyImproved
Use FedBCD-I, which allows offline local training before the intermittent cloud adjustmentFedBCD · CIFAR-10personalized test accuracyImproved
Use FedBCD-I, which allows offline local training before the intermittent cloud adjustmentFedBCD · CIFAR-10global test accuracyNo clear effect
Replace synchronous cloud aggregation with asynchronous first-available cloud-server aggregationFedBCD · MNISTruntime to improve model performanceImproved
Use asynchronous cloud updatesFedBCD-I · MNISTruntime to reach global performanceImproved
Decrease the fraction of cloud servers participating in each updateAsync-cloud FedBCD · MNISTupdate progress per roundHurt
Increase data-label diversityFedBCD · MNISTsmoothness of global performance improvementImproved
Use the rigorous asynchronous protocol, which performs isolated updates on servers outside the selected group (ablation)Async-cloud FedBCD · FedBCD protocol comparisonperformanceNo clear effect
Allow local models to deviate from the global model rather than enforcing model consensusFedBCD and FedBCD-I · MNIST and CIFAR-10global test accuracyMixed

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