AI Paper Atlas

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

CalFAT: Calibrated Federated Adversarial Training with Label Skewness

Chen Chen, Yuchen Liu, Xingjun Ma, Lingjuan Lyu

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 14 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
replace standard CE with calibrated logits loss in all FAT methods (MixFAT) (ablation)MixFAT · CIFAR10natural accuracy: 53.35 -> 60.23Improved
add calibration loss to FedMART (ablation)FedMART · CIFAR10PGD-20 robust accuracy: 18.10 -> 27.19Improved
calibration loss instead of LogitAdj (ablation)MixFAT · CIFAR10natural accuracy: 57.53 -> 60.23Improved
calibration loss instead of RoBal (ablation)MixFAT · CIFAR10PGD-20 robust accuracy: 27.86 -> 28.67Improved
add calibrated CE loss (ablation)CalFAT · CIFAR10 beta=0.05PGD-20 robust accuracy: 20.55 -> 29.49Improved
add calibrated KL loss (ablation)CalFAT · CIFAR10 beta=0.05PGD-20 robust accuracy: 27.59 -> 29.49Improved
increase adversarial data ratio from 0 to 1 (ablation)CalFAT · CIFAR10PGD-20 robust accuracy: 3.47 -> 31.19Improved
CalFAT vs best baseline FedGAIRATCalFAT · SVHNnatural accuracy: 58.41 -> 84.15Improved
CalFAT vs best baselineCalFAT · ImageNet subsetPGD-20 robust accuracy: 19.18 -> 19.97Improved

Later papers that compared with this method

1 later accepted paper reports CalFAT as a baseline in their results tables; 1 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