AI Paper Atlas

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

EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients

Meihan Wu, Tao Chang, Cui Miao, Jie Zhou, Chun Li, Xiangyu Xu, Ming Li, Xiaodong Wang

ICCV 2025 · Federated learning and privacy › Communication-efficient FL · approach: Communication-efficient heterogeneous FL · 4 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 masking ratio from 0.00 to 0.75 (ablation)EFTViT · client training costGFLOPs: 12.005 -> 2.997Improved
increase masking ratio to 0.95 (beyond 0.75) (ablation)EFTViT · CIFAR-100accuracyHurt
increase masking ratio from 0 to 75% (ablation)EFTViT · CIFAR-100accuracy: accuracy remains larger than 90%No clear effect
use 4 local layers instead of 2 (ablation)EFTViT · CIFAR-100accuracy: 90.81 -> 90.14Hurt
use 6 local layers instead of 2 (ablation)EFTViT · CIFAR-100accuracy: 90.81 -> 89.37Hurt
use 6 local layers instead of 2 (ablation)EFTViT · UC Merced Land-Useaccuracy: 98.80 -> 97.38Hurt
use 4 local layers instead of 2 (ablation)EFTViT · CIFAR-10accuracy: 98.35 -> 97.56Hurt
raise median sampling threshold higher (ablation)EFTViT · CIFAR-10/100, UC MercedaccuracyNo clear effect
hierarchical masked training vs FedRAEFTViT · UC Merced Land-Use (beta=0.1)accuracy: 96.43 -> 98.80Improved
hierarchical masked training vs FedRAEFTViT · UC Merced Land-Userounds to 85% accuracy: 55 -> 6Improved
hierarchical masked training vs FedRAEFTViT · UC Merced Land-Usetraining time per round (s): 6.436 -> 2.025Improved
hierarchical masked training vs Fed-LoRAEFTViT · CIFAR-100 (beta=0.1)accuracy: 70.23 -> 90.02Improved

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