AI Paper Atlas

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

Sharp Bounds for Sequential Federated Learning on Heterogeneous Data

Yipeng Li, Xinchen Lyu

JMLR 2025 · Federated learning and privacy › Communication-efficient FL · approach: Client participation analysis · 0 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
use sequential FL instead of parallel FLCNN federated training · Fashion-MNIST (C=1)test accuracy: 85.77 -> 87.60Improved
use sequential FL instead of parallel FLCNN federated training · Fashion-MNIST (C=2)test accuracy: 88.55 -> 89.66Improved
use sequential FL instead of parallel FLCNN federated training · Fashion-MNIST (C=5)test accuracy: 90.70 -> 90.92Improved
use sequential FL instead of parallel FLVGG-9 federated training · CIFAR-10 (C=1)test accuracy: 73.84 -> 81.05Improved
use sequential FL instead of parallel FLVGG-9 federated training · CIFAR-10 (C=2)test accuracy: 78.99 -> 83.34Improved
use sequential FL instead of parallel FLVGG-9 federated training · CIFAR-10 (C=5)test accuracy: 83.47 -> 84.73Improved
use sequential FL instead of parallel FLVGG-9 federated training · CINIC-10 (C=1)test accuracy: 52.27 -> 61.52Improved
use sequential FL instead of parallel FLVGG-9 federated training · CINIC-10 (C=2)test accuracy: 61.96 -> 67.31Improved
use sequential FL instead of parallel FLVGG-9 federated training · CINIC-10 (C=5)test accuracy: 68.45 -> 70.82Improved
use sequential FL instead of parallel FL on one-dimensional quadratics with learning rate of SFL set to half of PFLSFL vs PFL · Quadratic functions (10 groups, M=2, K=10)convergence of objectiveMixed
use sequential FL instead of parallel FL under high heterogeneity (C=1)SFL vs PFL · Logistic regression a9a and w8a (M=1000)training lossImproved
use sequential FL instead of parallel FL under low heterogeneity (C=2)SFL vs PFL · Logistic regression a9a and w8a (M=1000)training lossNo 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