AI Paper Atlas

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

Toward Enhancing Representation Learning in Federated Multi-Task Settings

Mehdi Setayesh, Mahdi Beitollahi, Yasser H. Khalil, Hongliang Li

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 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
align all models jointly with Muscle loss rather than baselinesFedMuscle · Setup1 Pascal VOC publicDelta (%): +5.83 (CoFED) -> +26.70Improved
use Muscle loss instead of Gramian-based contrastive loss (ablation)FedMuscle · Setup1 Pascal VOC, COCO, CIFAR-100Delta (%): +11.2%, +28.4%, +11.1%Improved
use pairwise alignment instead of Muscle loss within FedMuscle (ablation)FedMuscle · Setup1Delta (%)Hurt
replace CreamFL contrastive regularization with Muscle lossCreamFL · 1K and 5K test images retrievalDelta (%): +0.93 -> +1.17 (1K); +0.88 -> +1.94 (5K)Improved
use public dataset with detailed images (Pascal VOC, COCO) instead of CIFAR-100 (ablation)FedMuscle · Setup1Delta (%): +16.88 -> +26.70 / +28.65Improved
increase number of selected representation matrices M from 3 to 5 (ablation)FedMuscle · Setup1 Pascal VOCDelta (%): +26.70 -> +27.74No clear effect
increase M from 1 to 3 (ablation)FedMuscle · Setup1 Pascal VOCDelta (%): +17.90 -> +26.70Improved
add text and segmentation users (Setup2)FedMuscle · Setup2 DistilBERT TC useraccuracy: 56.03 -> 54.10Hurt
increase number of communication rounds (ablation)FedMuscle · Setup1 COCO publicDelta (%)Improved
increase CL epochs at low communication rounds (ablation)FedMuscle · Setup1 COCO publicDelta (%)Improved
increase batch size (ablation)FedMuscle · Setup1 COCO publicDelta (%)Improved

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