AI Paper Atlas

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

FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift

Yong Zhang, Feng Liang, Guanghu Yuan, Min Yang, Chengming Li, Xiping Hu

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 3 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
add prototype mixing plus Bernoulli masking before upload (ablation)FedPall · Office-10 (privacy study)top-1 accuracy: 65.76 -> 67.55Improved
add prototype mixing plus Bernoulli masking before upload (ablation)FedPall · Office-10 (privacy study)mutual information (DEMINE): 2.96 -> 2.10Improved
add Bernoulli masking on top of prototype mixture (ablation)FedPall · Office-10 (privacy study)top-1 accuracy: 64.46 -> 67.55Improved
add prototype mixture on top of Bernoulli masking (ablation)FedPall · Office-10 (privacy study)top-1 accuracy: 63.70 -> 67.55Improved
add KL and InfoNCE losses to CE loss (ablation)FedPall · Office-10top-1 accuracy: nearly 4 percentage pointsImproved
add InfoNCE loss to CE loss alone (ablation)FedPall · Office-10top-1 accuracyHurt
add KL loss to CE loss alone (ablation)FedPall · Office-10top-1 accuracyImproved
add KL loss to CE loss alone (ablation)FedPall · PACStop-1 accuracyHurt
add global classifier trained on mixed features (ablation)FedPall · Office-10 (Caltech)top-1 accuracy: 49.33% on Caltech, a 15.55% improvementImproved
add global classifier trained on mixed features (ablation)FedPall · Digits (MNIST-M)top-1 accuracy: 3.61% higherImproved
add global classifier trained on mixed features (ablation)FedPall · PACStop-1 accuracy: gains of up to 3%Improved
add global classifier trained on mixed features (ablation)FedPall · Digitstop-1 accuracyMixed

Later papers that compared with this method

2 later accepted papers report FedPall 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