AI Paper Atlas

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

FedFA: Federated Feature Augmentation

Tianfei Zhou, Ender Konukoglu

ICLR 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 8 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
Adding FedFA (federation-aware feature statistic augmentation) to FedAvgFedAvg on Office-Caltech 10 · Office-Caltech 10Top-1 accuracy average (%): +4.6 over FedAvg (78.5 to 83.1)Improved
Adding FedFA to FedAvgFedAvg on DomainNet · DomainNetTop-1 accuracy average (%): +3.7 over FedAvg (62.8 to 66.5)Improved
Adding FedFA to FedAvgFedAvg on CIFAR-10 and EMNIST · CIFAR-10 Dir(0.6), Dir(0.3), EMNISTTop-1 accuracy (%): +3.0 (Dir 0.6), +2.7 (Dir 0.3), +2.9 (EMNIST) over FedAvgImproved
Adding FedFA to FedAvg in federated domain generalization to unseen clientsFedAvg · Office-Caltech 10, DomainNet, ProstateMRI leave-one-client-outaverage accuracy/Dice (%): +3.9 Office, +2.2 DomainNet (approx from table averages 60.4->64.3, 47.5->51.2), +5.2 ProstateMRI (72.3->77.5)Improved
Random statistic perturbation with fixed std (FedFA-R) instead of federation-aware variances (ablation)FedAvg · DomainNet and ProstateMRIaccuracy / Dice (%): DomainNet 62.8 to 61.0; ProstateMRI 86.5 to 86.1; Office no change (78.5 to 78.6)Hurt
Using client-specific variances only (FedFA-C) instead of full federation-aware variances (ablation)FedFA · Office-Caltech 10, DomainNet, ProstateMRIaccuracy / Dice (%): Office 83.1 to 79.5; DomainNet 66.5 to 63.7; ProstateMRI 89.5 to 87.8Hurt
Direct fusion of client-specific and client-sharing variances instead of adaptive (t-distribution) fusion (ablation)FedFA · Office-Caltech 10, DomainNet, ProstateMRIaccuracy / Dice (%): Office 83.1 to 80.6; DomainNet 66.5 to 64.1; ProstateMRI 89.5 to 86.9Hurt
Adding FedFA on top of conventional augmentation (MixStyle, Mixup, M-Mixup, MoEx) (ablation)FedAvg with traditional augmentation · Office-Caltech 10, DomainNet, ProstateMRIaccuracy / Dice (%): e.g. Office MixStyle 79.9 to FedFA+MixStyle 84.0; ProstateMRI 88.5 to 90.2Improved
Applying FFA to more convolutional stages (set {1,2,3,4,5} vs single stage) (ablation)FedFA · Office-Caltech 10, DomainNet, ProstateMRIaccuracy / Dice (%): Single stage {1}: Office 78.8, DomainNet 63.5, ProstateMRI 88.5; all five stages: 83.1, 66.5, 89.5Improved
Adding FedFA to FedAvg in mini-ProstateMRI small-data settingFedAvg · mini-ProstateMRI (1/6 of training data)Dice (%): +3.0 over FedAvgImproved
Adding FedFA to FedAvg with local data reduced to 1/6 (mini-ProstateMRI)FedAvg · mini-ProstateMRIDice (%): +3.0 (absolute values not given in text)Improved

Later papers that compared with this method

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

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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