AI Paper Atlas

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

Decoupling Shared and Personalized Knowledge: A Dual-Branch Federated Learning Framework for Multi-Domain with Non-IID Data

Yiran Pang, Zhen Ni, Xiangnan Zhong

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 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 dual-branch private/shared split with local pre-training (pFedDB) instead of FedAvgFedAvg · DomainNet (avg)accuracy (%): 41.5 -> 50.3Improved
add two-phase training (local pretraining before federation) (ablation)pFedDB · Office-Caltech-10 (avg)accuracy (%): 71.1 -> 73.4Improved
add two-phase training (local pretraining before federation) (ablation)pFedDB · Chest-X-Ray-4 (avg)accuracy (%): 81.3 -> 83.4Improved
use element-wise addition instead of attention fusion (ablation)pFedDB · Office-Caltech-10 (avg)accuracy (%): 70.5 -> 73.4Improved
use element-wise addition instead of weighted sum alpha=0.5 (ablation)pFedDB · Office-Caltech-10 (avg)accuracy (%): 72.7 -> 73.4Improved
set cut depth so shared branch has about 70% of parameters instead of 99% (ablation)pFedDB · Chest-X-Ray-4 (avg)accuracy (%): 82.7 -> 83.4Improved
set cut depth to share 71% of parameters instead of only 4% (ablation)pFedDB · Office-Caltech-10 (avg)accuracy (%): 66.8 -> 73.4Improved
communicate only the shared branchpFedDB · three backbonesper-round communication: 30-37% fewer bytes per roundImproved
freeze shared branch for newly joining client rather than fine-tune all (ablation)pFedDB · MNIST-M and Sketch new-client adaptationvalidation accuracyImproved
compare pFedDB to FedWon on the SVHN clientpFedDB · Digits-Five (Sv)accuracy (%): 71.3 -> 68.6Mixed
use TinyViT backbone instead of AlexNetpFedDB · Office-Caltech-10 (avg)accuracy (%): Single 73.5 -> 75.9Improved

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