AI Paper Atlas

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

Domain-Skewed Federated Learning with Feature Decoupling and Calibration

Huan Wang, Jun Shen, Jun Yan, Guansong Pang

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 0 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 domain-aware aggregation (ablation)F2DC · PACSAVG accuracy: 75.33 -> 76.47Improved
Add domain-aware aggregation (ablation)F2DC · Office-CaltechAVG accuracy: 65.29 -> 66.82Improved
Plug DFD and DFC into FedAvgFedAvg · PACSAVG accuracy: +8.94Improved
Plug DFD and DFC into FedHEALFedHEAL · PACSAVG accuracy: +1.72Improved
Plug DFD and DFC into FDSEFDSE · PACSAVG accuracy: +1.66Improved
Use corrected features f* vs domain-related features f- (ablation)F2DC · PACSAVG accuracy: 57.87 -> 73.49Improved
Combine f+ with corrected f* instead of f+ alone (ablation)F2DC · PACSAVG accuracy: 75.13 -> 76.47Improved
Contrastive alignment to global representation (MOON, FedRCL)FedAvg · PACSAVG accuracy: 66.39 -> 62.64Hurt
Use very small temperature tau=0.02 to force all signals into f+ (ablation)F2DC · Office-Caltech, PACSAVG accuracyHurt
Set mask smoothness sigma too small or too large (ablation)F2DC · PACSAVG accuracyHurt
Extremely large lambda1 or lambda2 (ablation)F2DC · Office-Caltech, PACSAVG accuracyHurt
Add decoupler and corrector computationF2DC · PACStraining time per round: 176.94s (FedAvg) vs 180.67sMixed

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