AI Paper Atlas

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

FedDC: Federated Learning With Non-IID Data via Local Drift Decoupling and Correction

Liang Gao, Huazhu Fu, Li Li, Yingwen Chen, Ming Xu, Cheng-Zhong Xu

CVPR 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 365 citations (OpenAlex)

Check 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
Track and correct client parameter drift with a local drift variableFedDC · CIFAR100-iid, 100 clients, full participationcommunication rounds to 40% accuracy: 56 -> 37Improved
Track and correct client parameter drift with a local drift variableFedDC · CIFAR10-D2, 100 clients, full participationtest accuracy: 79.14 -> 84.32Improved
Add the penalized term to the FedDC local objective (ablation)FedDC(le) · CIFAR10, iid and non-iid, 100 clients, 15% participationtest accuracyImproved
Add the gradient correction term to the FedDC objective with the penalized term (ablation)FedDC(lelp) · CIFAR10, iid and non-iid, 100 clients, 15% participationtest accuracyImproved
Omit the penalized term that constrains the drift variable (ablation)FedDC(le) and FedDC(lelg) · CIFAR10, iid and non-iid, 100 clients, 15% participationtest accuracyHurt
Increase the penalized-term weight to 0.5 or 1 (ablation)FedDC · MNIST and CIFAR10, 100 clients, 15% participationconvergence performanceHurt
Use partial client participation at 15% instead of full participationFedDC · CIFAR10-iid, 100 clientstest accuracy: 86.18% -> 85.71%Hurt

Later papers that compared with this method

5 later accepted papers report FedDc as a baseline in their results tables; 4 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