AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients

Shangchao Su, Bin Li, Xiangyang Xue

ECCV 2024 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 18 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 fixed-prefix depth allocation (InclusiveFL) with random layer allocation (FedRA)heterogeneous federated tuning · DomainNet feature-skew (ViT)average accuracy (%): 55.97 -> 63.90Improved
replace fixed-prefix allocation with random allocationheterogeneous federated tuning · NICO++ feature-skew (MLP-Mixer)average accuracy (%): 72.28 -> 77.57Improved
random allocation under 30 clients with label skewFedRA · NICO++ feature&label-skew (ViT)average accuracy (%): 83.03 -> 85.44Improved
use random allocation when all clients are smaller than the server modelFedRA · NICO++ (ViT, clients with 6 layers)average accuracy (%): 20.58 -> 70.38Improved
random allocation under dynamic heterogeneityFedRA · NICO++ dynamic heterogeneity (ViT)average accuracy (%): 88.73 -> 89.74Improved
use constrained allocation (each layer to at least one client) instead of previous-round substitution (ablation)FedRA · NICO++ (ViT, clients [6]*6)average accuracy (%): 70.38 -> 67.62Hurt
constrained allocation versus previous-round substitution with 10-layer clients (ablation)FedRA · NICO++ (ViT, clients [10]*6)average accuracy (%): 90.53 -> 90.54No clear effect
change LoRA insertion position (both, l0 only, l1 only) (ablation)FedRA · NICO++ (ViT)average accuracy (%): 86.48 / 86.38 / 85.65No clear effect
apply InclusiveFL/DepthFL versus ceiling on largest clientsInclusiveFL, DepthFL · DomainNet feature-skew (ViT, clipart 12 layers)accuracy (%): 85.01 -> 81.13Hurt
FedRA versus InclusiveFL on grass domain quickdraw (hard domain)FedRA · DomainNet feature-skew (ViT, quickdraw)accuracy (%): 73.69 (ceiling) vs 25.41 (FedRA)Mixed

Later papers that compared with this method

2 later accepted papers report FedRA as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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