AI Paper Atlas

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

BAFFLE: A Baseline of Backpropagation-Free Federated Learning

Haozhe Feng, Tianyu Pang, Chao Du, Wei Chen, Shuicheng Yan, Min Lin

ECCV 2024 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 26 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 perturbations K (ablation)BAFFLE · CIFAR-10 (iid, WRN-10-2)accuracy (%): 52.27 -> 58.63Improved
increase K from 2000 to 5000 (ablation)BAFFLE · CIFAR-10 (WRN-10-2)accuracy: barely improves by 2%No clear effect
add EMA on global parameters (ablation)BAFFLE · MNIST (WRN-10-2, K=100)accuracy (%): 85.89 -> 88.35Improved
use Hardswish instead of ReLU (ablation)BAFFLE · MNIST (WRN-10-2, K=100)accuracy (%): 79.08 -> 88.35Improved
use Hardswish instead of SELU (ablation)BAFFLE · CIFAR-10 (WRN-10-2, K=200)accuracy (%): 43.37 -> 52.27Improved
use twice forward difference instead of central scheme at equal forward cost (ablation)BAFFLE · CIFAR-10 (WRN-10-2, K=200)accuracy (%): 42.89 -> 52.27Improved
label non-iid clients (Dirichlet 0.3, 100 clients) vs iidBAFFLE · CIFAR-10 / CIFAR-100accuracy: drop of 14% on CIFAR-10 and 16% on CIFAR-100Hurt
increase K on OfficeHome finetuning (ablation)BAFFLE · OfficeHome (MobileNet)average Top-1 accuracy (%): 56.91 -> 66.98Improved
use BAFFLE layer-by-layer inference instead of backpropagationFL clients · GPU memory CIFAR-10/100 (LeNet)GPU memory (MB): 1680 -> 67~174Improved
replace backpropagation with BAFFLE (backprop-free)FL training · CIFAR-100 (iid, WRN-10-2)accuracy (%): 60.08 -> 53.15Hurt

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