AI Paper Atlas

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

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

Samiul Alam, Luyang Liu, Ming Yan, Mi Zhang

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 45 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
rolling sub-model extraction instead of static (HeteroFL)partial training FL · CIFAR-10 high heterogeneityglobal accuracy: 63.90 -> 69.44Improved
rolling sub-model extraction instead of random (Federated Dropout)partial training FL · CIFAR-10 high heterogeneityglobal accuracy: 46.64 -> 69.44Improved
rolling extraction vs Federated Dropoutpartial training FL · CIFAR-10 low heterogeneityglobal accuracy: 76.20 -> 84.45Improved
rolling extraction vs HeteroFLpartial training FL · Stack Overflowglobal accuracy: 27.21 -> 29.22Improved
FedRolex vs KD-based Fed-ET with public dataFedRolex · CIFAR-10 high heterogeneityglobal accuracy: 78.66 -> 69.44Hurt
FedRolex vs Fed-ET without public dataFedRolex · CIFAR-100 high heterogeneityglobal accuracy: 35.78 -> 56.57Improved
model-heterogeneous FedRolex vs homogeneous upper boundFedRolex · Stack Overflowglobal accuracy: 29.79 -> 29.55No clear effect
add client weighting schemes to selective averaging (ablation)FedRolex · CIFAR-10 high heterogeneityglobal accuracy: 69.44 -> 69.09No clear effect
vary client participation rate from 5% to 20%FedRolex · CIFAR-10 high heterogeneityglobal accuracy: 57.90 -> 71.85Improved
vary overlap between rolling windows (ablation)FedRolex · CIFAR-10/100global accuracyNo clear effect
increase global model size to 2-16x client model (ablation)FedRolex · CIFAR-10/100global accuracyHurt
increase fraction of large-capacity clients beyond a small share (ablation)FedRolex · CIFAR/Stack Overflowglobal accuracyNo clear effect

Later papers that compared with this method

6 later accepted papers report FedRolex as a baseline in their results tables; 6 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