AI Paper Atlas

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

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement

Jieming Bian, Lei Wang, Letian Zhang, Jie Xu

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 34 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
apply residual correction to B instead of to A (ablation)LoRA-FAIR · DomainNet ViTaverage accuracy: 76.42 -> 77.07Improved
apply residual correction to B instead of to both A and B (ablation)LoRA-FAIR · DomainNet ViTaverage accuracy: 75.55 -> 77.07Improved
add regularization term (lambda = 0.01 instead of 0) (ablation)LoRA-FAIR · DomainNet ViTaverage accuracy: 73.22 -> 77.07Improved
vary regularization weight among small positive values (0.01, 0.02) (ablation)LoRA-FAIR · DomainNet ViTaverage accuracyNo clear effect
use LoRA-FAIR instead of FLoRA with 2 local epochsFLoRA · DomainNet ViTaverage accuracy: 75.53 -> 77.07Improved
use LoRA-FAIR instead of FLoRA with 10 local epochsFLoRA · DomainNet ViTaverage accuracy: 73.60 -> 74.31Improved
add LoRA-FAIR on top of HETLoRA for heterogeneous ranksHETLoRA · DomainNet ViTaverage accuracy: 60.89 -> 74.22Improved
add LoRA-FAIR on top of FlexLoRA in heterogeneous ranksFlexLoRA · DomainNet ViTaverage accuracy: 73.50 -> 74.22Improved
use LoRA-FAIR instead of FedIT (feature non-IID)FedIT · DomainNet MLP-Mixeraverage accuracy: 64.37 -> 65.87Improved
use LoRA-FAIR instead of FlexLoRA (label non-IID)FlexLoRA · DomainNet MLP-Mixeraverage accuracy: 61.20 -> 62.28Improved
freeze A and train only B (FFA-LoRA) instead of FedITFedIT · DomainNet MLP-Mixer (label non-IID)average accuracy: 60.77 -> 52.88Hurt
use LoRA-FAIR instead of FLoRA on NICO++ (feature non-IID)FLoRA · NICO++ ViTaverage accuracy: 90.93 -> 91.24Improved

Later papers that compared with this method

2 later accepted papers report LoRA-FAIR 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