AI Paper Atlas

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

Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM

Ziba Parsons, Fei Dou, Houyi Du, Zheng Song, Jin Lu

NeurIPS 2023 · Federated learning and privacy › Communication-efficient FL · approach: Client participation analysis · 1 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 RWSADMM instead of Dittopersonalized FL · MNIST, MLRtest accuracy (%): 97.37 \pm 0.02 -> 98.63 $ \pm $ 0.01Improved
Use RWSADMM instead of pFedMepersonalized FL · MNIST, MLPtest accuracy (%): 99.46$\pm$ 0.01 -> 99.29 $ \pm $ 0.02Hurt
Use RWSADMM instead of Dittopersonalized FL · MNIST, CNNtest accuracy (%): 99.20 \pm 0.11 -> 99.52 $ \pm $ 0.04Improved
Use RWSADMM instead of Dittopersonalized FL · Synthetic, MLRtest accuracy (%): 86.24 \pm 0.03 -> 96.44 $ \pm $ 0.12Improved
Use RWSADMM instead of pFedMepersonalized FL · Synthetic, MLPtest accuracy (%): 86.36\pm 0.15 -> 97.17 $ \pm $ 0.18Improved
Use RWSADMM instead of Dittopersonalized FL · CIFAR10, MLRtest accuracy (%): 75.2 \pm 0.01 -> 80.72 $\pm $ 0.11Improved
Use RWSADMM instead of Dittopersonalized FL · CIFAR10, MLPtest accuracy (%): 81.37 \pm 0.13 -> 84.99 $ \pm $ 0.20Improved
Use RWSADMM instead of Dittopersonalized FL · CIFAR10, CNNtest accuracy (%): 83.86 \pm 0.02 -> 87.08 $ \pm $ 0.03Improved
Use random-walk server movement and stochastic ADMM updatesmobilizing personalized FL · MNIST, MLP and CNNconvergence iterations: 200 iterations -> 600 iterationsImproved
Use RWSADMM instead of FedAvgmobilizing FL · MNIST, MLRtraining time (s): 384 -> 500Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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