AI Paper Atlas

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

DENSE: Data-Free One-Shot Federated Learning

Jie Zhang, Chen Chen, Bo Li, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chunhua Shen, Chao Wu

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 33 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 BN loss and boundary-support loss to CE generator loss (ablation)DENSE generator · CIFAR10accuracy (%): 53.12 -> 62.19Improved
add BN loss and boundary-support loss to CE generator loss (ablation)DENSE generator · SVHNaccuracy (%): 73.11 -> 80.03Improved
add BN loss and boundary-support loss to CE generator loss (ablation)DENSE generator · CIFAR100accuracy (%): 36.47 -> 42.07Improved
add BN regularization loss to generator (ablation)DENSE · CIFAR10accuracy (%): 61.05 -> 62.19Improved
add BN regularization loss to generator (ablation)DENSE · CIFAR100accuracy (%): 39.89 -> 42.07Improved
add boundary support (divergence) loss to generator (ablation)DENSE · CIFAR10accuracy (%): 59.18 -> 62.19Improved
add boundary support (divergence) loss to generator (ablation)DENSE · SVHNaccuracy (%): 77.59 -> 80.03Improved
use LDAM in clients' local trainingDENSE · CIFAR10 alpha=0.1accuracy (%): 50.26 -> 57.24Improved
use LDAM in clients' local trainingDENSE · SVHN alpha=0.5accuracy (%): 80.03 -> 81.77Improved
add more communication rounds (1 to 5)DENSE · CIFAR10 alpha=0.5accuracy (%): 63.89 -> 76.01Improved
distill ensemble with synthetic data instead of FedAvg parameter averagingDENSE · CIFAR10 alpha=0.3accuracy (%): 27.72 -> 59.76Improved
increase number of clients from 5 to 100DENSE · CIFAR10accuracy (%): 62.19 -> 43.28Hurt

Later papers that compared with this method

9 later accepted papers report DENSE as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

1 more not listed.

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