AI Paper Atlas

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

FedSR: A Simple and Effective Domain Generalization Method for Federated Learning

A. Tuan Nguyen, Philip Torr, Ser-Nam Lim

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 13 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
add L2R and CMI regularizers on representation to FedAVG (FedSR)FedAVG · PACSaverage accuracy: 80.3 -> 83.7Improved
add L2R and CMI regularizers to FedAVGFedAVG · DomainNetaverage accuracy: 39.6 -> 41.3Improved
add L2R and CMI regularizers to FedAVGFedAVG · OfficeHomeaverage accuracy: 67.9 -> 69.3Improved
add L2R and CMI regularizers to FedAVGFedAVG · RotatedMNISTaverage accuracy: 94.5 -> 96.7Improved
add CMI regularizer on top of L2R (FedSR vs FedL2R) (ablation)FedSR · PACSaverage accuracy: 83.1 -> 83.7Improved
add CMI regularizer on top of L2R (FedSR vs FedL2R) (ablation)FedSR · OfficeHomeaverage accuracy: 68.8 -> 69.3Improved
add CMI regularizer on top of L2R (FedSR vs FedL2R) (ablation)FedSR · DomainNetaverage accuracy: 40.6 -> 41.3Improved
add L2R on top of CMI (FedSR vs FedCMI) (ablation)FedSR · PACSaverage accuracy: 81.7 -> 83.7Improved
FedCMI alone vs FedAVG (ablation)FedAVG · OfficeHomeaverage accuracy: 67.9 -> 67.8No clear effect
FedL2R alone vs FedAVG (ablation)FedAVG · PACSaverage accuracy: 80.3 -> 83.1Improved

Later papers that compared with this method

7 later accepted papers report FedSR as a baseline in their results tables; 7 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