AI Paper Atlas

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

A Unified Analysis of Federated Learning with Arbitrary Client Participation

Shiqiang Wang, Mingyue Ji

NeurIPS 2022 · Federated learning and privacy › Communication-efficient FL · approach: Client participation analysis · 16 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 update amplification (eta=10, P=500) to FedAvg (ablation)Generalized FedAvg (Algorithm 1) · FashionMNIST and CIFAR-10, periodic client availabilitytest performance (plotted)Improved
replace amplified Algorithm 1 with wait-for-all using minibatch gradients (ablation)Algorithm 1 with amplification · FashionMNIST and CIFAR-10test performance (plotted)Hurt
use full-dataset gradients (wait-full) instead of minibatch gradients in the wait-for-all method (ablation)wait-for-all baseline · FashionMNIST and CIFAR-10test performance (plotted)No clear effect
use amplification interval P=1 instead of P=500 with eta=10 (ablation)Algorithm 1 with amplification · FashionMNIST and CIFAR-10test performance (plotted)Hurt
use P=100 or P=300 instead of P=500 (matching participation cycle) (ablation)Algorithm 1 with amplification, eta=10 · FashionMNIST and CIFAR-10test performance (plotted)No clear effect
increase P to 700 or 900 beyond the participation cycle of 500 (ablation)Algorithm 1 with amplification, eta=10 · CIFAR-10test performance (plotted)Hurt
use regularized participation (equal averaged weights over P rounds) in theoryGeneralized FedAvg convergence bound · theory, nonconvexconvergence error boundImproved

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