AI Paper Atlas

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

SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training

Enmao Diao, Jie Ding, Vahid Tarokh

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 36 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
fine-tune the aggregated global model with labeled server data each round (ablation)SemiFL · CIFAR10 4000 labels, IIDaccuracy: 47.03 -> 93.10Improved
generate pseudo-labels once with the received global model (ablation)SemiFL · CIFAR10 4000 labels, IIDaccuracy: 81.70 -> 93.10Improved
fine-tune global model with labeled data (ablation)SemiFL · CIFAR10 4000 labels, Non-IID K=2accuracy: 48.89 -> 85.34Improved
generate pseudo-labels with global model (ablation)SemiFL · CIFAR10 4000 labels, Non-IID K=2accuracy: 80.42 -> 85.34Improved
alternate training (both components) over vanilla FedAvg + FixMatch (ablation)FedAvg + FixMatch · CIFAR10 4000 labels, IIDaccuracy: 40.26 -> 93.10Improved
use 5 local epochs instead of 1 (ablation)SemiFL · CIFAR10 4000 labels, IIDaccuracy: 88.9(0.3) -> 93.1(0.1)Improved
add Mixup data augmentation (ablation)SemiFL · CIFAR10 4000 labels, IIDaccuracy: 91.3(0.2) -> 93.1(0.1)Improved
add global momentum 0.5 (ablation)SemiFL · CIFAR10 4000 labels, IIDaccuracy: 92.4(0.1) -> 93.1(0.1)Improved
add global momentum 0.5 (ablation)SemiFL · CIFAR10 4000 labels, Non-IID K=2accuracy: 85.4(0.6) -> 85.3(0.3)No clear effect
update sBN statistics with server and clients instead of server only (ablation)SemiFL · CIFAR10 4000 labels, IIDaccuracy: 93.1(0.2) -> 93.1(0.1)No clear effect
SemiFL instead of existing SSFL methods (FedMatch)FedMatch · CIFAR10 4000 labels, IIDaccuracy: 58.6(0.5) -> 93.1(0.1)Improved

Later papers that compared with this method

2 later accepted papers report SemiFL 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