AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Scaling Unsupervised Multi-Source Federated Domain Adaptation through Group-Wise Discrepancy Minimization

Larissa Reichart, Cem Ata Baykara, Ali Burak Ünal, Harlin Lee, Mete Akgün

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 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
replace FACT's single-pair discrepancy with GALA's group discrepancy and weightingFACT · Digit-18 (9 targets)average accuracy (%): 87.6 -> 92.9Improved
use GALA instead of FACT on svhn-xsFACT · Digit-18 svhn-xsaccuracy (%): 79.1 -> 88.6Improved
use GALA instead of FACT on synmFACT · Digit-18 synmaccuracy (%): 79.4 -> 85.8Improved
use GALA instead of FACT on Digit-FiveFACT · Digit-Fiveaverage accuracy (%): 95.0 -> 95.4Improved
use GALA instead of KD3A on Office-Caltech10KD3A · Office-Caltech10average accuracy (%): 97.9 vs 97.8No clear effect
increase number of sources beyond 9FACT · Digit-Five targetsaccuracyHurt
use temperature tau=0.2 instead of 0.8-1.0 (ablation)GALA · Digit-18accuracyHurt
use tau=3 instead of 0.8-1.0 (ablation)GALA · Digit-18accuracyHurt
add MDMGB+ weighting to IGD (ablation)GALA · Digit-18 svhn-xsconvergence/accuracyImproved
add MDMGB weighting to IGD instead of uniform weights (ablation)IGD · Digit-18 svhn-xsaccuracyNo clear effect
add IGD target training to weighting on mnistm (ablation)GALA · Digit-18 mnistmaccuracyImproved
use GALA instead of KD3A for runtime at 9 sourcesKD3A · Digit-Five scalabilityseconds per round: 5600.48 -> 22.37Improved

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