AI Paper Atlas

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

FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments

Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 2 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 global representation sharing with dual encoder (ablation)FedDAG* · CIFAR-10 (20% label skew)accuracy (%): 88.67 -> 90.76Improved
add global representation sharing with dual encoder (ablation)FedDAG* · FMNIST (20% label skew)accuracy (%): 92.75 -> 93.82Improved
add global representation sharing with dual encoder (ablation)FedDAG* · SVHN (20% label skew)accuracy (%): 91.87 -> 93.91Improved
add global representation sharing with dual encoder (ablation)FedDAG* · CIFAR-100 (20% label skew)accuracy (%): 70.37 -> 72.84Improved
add cross-cluster sharing to a dual encoder (ablation)FedDAG-dagger · CIFAR-10 (20% label skew)accuracy (%): 88.79 -> 90.76Improved
add cross-cluster sharing to a dual encoder (ablation)FedDAG-dagger · SVHN (20% label skew)accuracy (%): 91.95 -> 93.91Improved
add a second encoder without sharing to the single-encoder model (ablation)FedDAG* · CIFAR-10 (20% label skew)accuracy (%): 88.67 -> 88.79No clear effect
add second encoder without sharing to the single-encoder model (ablation)FedDAG* · CIFAR-100 (20% label skew)accuracy (%): 70.37 -> 70.28No clear effect
combine data and gradient similarity for clustering instead of PACFL data-onlyFedDAG* · CIFAR-10 (20% label skew)accuracy (%): 86.93 -> 88.67Improved
combine data and gradient similarity instead of IFCA gradient-onlyFedDAG* · CIFAR-10 (20% label skew)accuracy (%): 86.64 -> 88.67Improved
use FedDAG instead of best baseline CFL-GP under concept shiftFedDAG · CIFAR-10 (concept shift)accuracy (%): 66.74 -> 69.90Improved
use FedDAG instead of IFCA under LDA skewFedDAG · CIFAR-10 (LDA skew, alpha 0.25)accuracy (%): 74.43 -> 77.84Improved

Later papers that compared with this method

1 later accepted paper reports FedDAG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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