AI Paper Atlas

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

Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?

Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan

AAAI 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
increase number of FL clients at fixed total computeViT MAE linear probing · CIFAR-100 and ImageNet (10% LP)optimal model size: slopes in [-0.28, -0.48], R2 > 0.88Hurt
switch from centralized to federated training with same dataViT MAE linear probing · CIFAR-100 and ImageNetLP accuracyHurt
increase number of clientsViT MAE linear probing · CIFAR-100LP accuracy gap to centralizedHurt
train on one client's data only vs full FLViT · CIFAR-100 and ImageNetoptimal model sizeNo clear effect
replace ViT with ResNetFL scaling analysis · CIFAR-100 and ImageNetoptimal model size trendNo 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