AI Paper Atlas

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

Single-Round Scalable Analytic Federated Learning

Alan T. L. Bacellar, Mustafa Munir, Felipe M. G. França, Priscila M. V. Lima, Radu Marculescu, Lizy K. John

CVPR 2026 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 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 SAFLe non-linear head instead of linear AFL headResNet-18 frozen backbone · CIFAR-10top-1 accuracy: 80.75 -> 90.73Improved
use SAFLe instead of multi-round DeepAFLResNet-18 · CIFAR-100top-1 accuracy: 66.98 -> 70.61Improved
use SAFLe instead of DeepAFLResNet-18 · Tiny-ImageNettop-1 accuracy: 62.35 -> 64.58Improved
make data more non-IID (alpha 0.1 -> 0.01)FedAvg · CIFAR-100top-1 accuracy: 56.62 -> 32.99Hurt
make data more non-IIDSAFLe · CIFAR-100top-1 accuracy: 70.61 in all four settingsNo clear effect
use Binary Overlapping bucketing instead of Integer (ablation)SAFLe · CIFAR-10 (Bn=8)top-1 accuracy: 78.15 -> 90.73Improved
use Binary Overlapping instead of OneHot bucketing (ablation)SAFLe · CIFAR-100 (Bn=8)top-1 accuracy: 61.66 -> 70.61Improved
increase bucket count from 8 to 20 with Integer bucketing (ablation)SAFLe · CIFAR-10top-1 accuracy: 78.15 -> 59.75Hurt
use many small embeddings (high E, low V) instead of few large ones (ablation)SAFLe · fixed model sizeaccuracyImproved
use many small embeddings (ablation)SAFLe · fixed model sizecommunication costHurt
swap ResNet-18 for ViT-B-16 backbone (ablation)SAFLe vs AFL · Tiny-ImageNettop-1 accuracy gain over AFL: 54.67 -> 64.58 (ResNet-18) vs 82.02 -> 82.71 (ViT-B-16)Mixed
use SAFLe instead of DeepAFLcommunication · CIFAR-100 at ~67% accuracytotal communication: 146MB -> 70MBImproved

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