AI Paper Atlas

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

The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics

Fabio Turazza, Marco Picone, Marco Mamei

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 2 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
model class-specific covariances (QDA instead of LDA) (ablation)GH-LDA · CIFAR-100-Caccuracy (%): 37.6% -> 64.3%Improved
use Fisher-space trainable head (FisherMix) instead of LDA (ablation)GH-LDA · CIFAR-100-Caccuracy (%): 37.6% -> 40.1%Improved
replace full QDA with LDA on clean CIFAR-10 (ablation)GH-QDA_full · CIFAR-10accuracy (%): 84.40 -> 86.05Improved
use Places365 instead of ImageNet pretraining for ResNet-18 (QDA vs LDA on CIFAR-100-C) (ablation)GH-LDA · CIFAR-100-Caccuracy (%): 37.6% -> 25.99Hurt
use ResNet50 backbone instead of VGG16 (ablation)GH-LDA · CIFAR-10accuracy (%): 81.39 -> 91.26Improved
use EfficientNet-B0 backbone instead of ResNet18 (ablation)GH-LDA · CIFAR-10accuracy (%): 86.17 -> 90.01Improved
use ResNet50 instead of ResNet18 with QDA (ablation)GH-QDA_full · CIFAR-10accuracy (%): 84.76 -> 86.68Improved
use full QDA instead of LDA in RP space (ablation)LDA · AG_NEWSaccuracy (%): 88.93 -> 68.20Hurt
increase DLR-QDA rank from 4 to 16 (ablation)DLR-QDA · AG_NEWSaccuracy (%): 67.08 -> 38.32Hurt
increase DLR-QDA rank from 4 to 16 (ablation)DLR-QDA · CIFAR-100 (RP space)accuracy (%): 49.99 -> 42.01Hurt
increase DLR-QDA rank from 4 to 16 (ablation)DLR-QDA · DBPEDIA-14accuracy (%): 92.32 -> 92.19No clear effect
use GH-LDA one-shot instead of FedAvg 1 roundFedAvg · CIFAR-10 (a=0.1)accuracy (%): 24.53 -> 86.05Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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