AI Paper Atlas

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

DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning

Kangyang Luo, Shuai Wang, Yexuan Fu, Xiang Li, Yunshi Lan, Ming Gao

NeurIPS 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 7 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
Fine-tune FedAvg with DFRDFedAvg · FMNIST, ω=1.0G.acc: 89.71{ $\pm$0.10} -> 91.65{ $\pm$0.09}Improved
Fine-tune FedAvg with DFRDFedAvg · SVHN, ω=1.0G.acc: 70.63{ $\pm$1.95} -> 77.84{ $\pm$1.39}Improved
Fine-tune FedAvg with DFRDFedAvg · CIFAR-10, ω=1.0G.acc: 67.16{ $\pm$0.98} -> 71.54{ $\pm$0.66}Improved
Fine-tune FedAvg with DFRDFedAvg · CIFAR-100, ω=1.0G.acc: 57.31{ $\pm$0.09} -> 61.49{ $\pm$0.28}Improved
Fine-tune FedRolex with DFRDFedRolex · SVHN, ρ=5G.acc: 34.71{ $\pm$13.68} -> 46.30{ $\pm$10.12}Improved
Fine-tune FedRolex with DFRDFedRolex · CIFAR-10, ρ=10G.acc: 16.57{ $\pm$4.40} -> 25.57{ $\pm$1.37}Improved
Fine-tune FedRolex with DFRDFedRolex · Tiny-ImageNet, ρ=10G.acc: 5.55{ $\pm$0.40} -> 6.80{ $\pm$0.11}Improved
Fine-tune FedRolex with DFRDFedRolex · FOOD101, ρ=10G.acc: 7.54{ $\pm$0.46} -> 10.58{ $\pm$0.29}Improved
Add an EMA copy of the generator (ablation)DFRD · SVHN, FedRolex+DFRD configurationG.acc: 26.97{ $\pm$12.28} -> 34.78{ $\pm$9.19}Improved
Add an EMA copy of the generator (ablation)DFRD · CIFAR-10, FedRolex+DFRD configurationG.acc: 19.80{ $\pm$2.25} -> 25.57{ $\pm$1.37}Improved
Add the transferability loss (ablation)DFRD · SVHN, FedRolex+DFRD configurationG.acc: 29.30{ $\pm$9.25} -> 34.78{ $\pm$9.19}Improved
Add the diversity loss (ablation)DFRD · SVHN, FedRolex+DFRD configurationG.acc: 27.68{ $\pm$9.75} -> 34.78{ $\pm$9.19}Improved

Later papers that compared with this method

1 later accepted paper reports DFRD 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