AI Paper Atlas

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

DELTA: Diverse Client Sampling for Fasting Federated Learning

Lin Wang, Yongxin Guo, Tao Lin, Xiaoying Tang

NeurIPS 2023 · Federated learning and privacy › Communication-efficient FL · approach: Client participation analysis · 8 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
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · FashionMNISTaccuracy (%): 71.69 ±0.43 -> 72.10 ±0.49Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs Cluster-based IS · FashionMNISTrounds to 70% accuracy: 362 -> 322Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs Cluster-based IS · FashionMNISTtime to 70% accuracy (s): 1547.41 -> 1372.33Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · CIFAR-10accuracy (%): 55.05 ±0.27 -> 55.20 ±0.26Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · CIFAR-10rounds to 54% accuracy: 313 -> 303Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · CIFAR-10time to 54% accuracy (s): 3085.05 -> 2989.98Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · FEMNISTaccuracy (%): 80.11 ±0.29 -> 81.44 ±0.28Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · FEMNISTrounds to 70% accuracy: 110 -> 98Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · FEMNISTtime to 70% accuracy (s): 223.27 -> 198.95Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · CelebAaccuracy (%): 88.12 ±0.71 -> 89.67 ±0.56Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · CelebArounds to 85% accuracy: 327 -> 306Improved
Replace gradient-norm importance sampling with diversity-and-local-variance samplingFedPracDELTA vs FedPracIS · CelebAtime to 85% accuracy (s): 2746.82 -> 2607.12Improved

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