AI Paper Atlas

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

Federated Learning with Profile Mapping under Distribution Shifts and Drifts

Mohan Li, Dario Fenoglio, Martin Gjoreski, Marc Langheinrich

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 1 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
use Feroma instead of best baseline CFLfederated aggregation · MNISTaccuracy: 76.6 -> 90.7Improved
use Feroma instead of CFLfederated aggregation · CIFAR-10accuracy: 33.9 -> 44.2Improved
use Feroma instead of FedEMfederated aggregation · CIFAR-100accuracy: 31.7 -> 39.9Improved
use Feroma instead of FedDriftfederated aggregation · CheXpertaccuracy: 72.3 -> 72.4No clear effect
use Feroma instead of FedDriftfederated aggregation · Office-Homeaccuracy: 42.1 -> 42.4No clear effect
use Feroma instead of CFL under high non-IID, every-round driftfederated aggregation · MNIST high 20/20accuracy: 74.5 -> 90.8Improved
scale to 100 clients with Feroma instead of best baseline CFLfederated aggregation · MNIST 100 clientsaccuracy: >10 pp over CFLImproved

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