AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

FedMix: Approximation of Mixup under Mean Augmented Federated Learning

Tehrim Yoon, Sumin Shin, Sung Ju Hwang, Eunho Yang

ICLR 2021 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 66 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
Use derivative-based FedMix with averaged external data instead of FedAvgFederated learning on CIFAR10 · CIFAR10test accuracy: 73.8 -> 81.2Improved
Use derivative-based FedMix with averaged external data instead of FedAvgFederated learning on CIFAR100 · CIFAR100test accuracy: 50.4 -> 56.7Improved
Use derivative-based FedMix with averaged external data instead of FedAvgFederated learning on FEMNIST · FEMNISTtest accuracy: 85.3 -> 86.5Improved
Add FedMix to FedProxFedProx · CIFAR10test accuracy: 77.3 -> 78.9Improved
Use NaiveMix instead of FedAvgFederated learning · CIFAR10test accuracy: 73.8 -> 77.4Improved
Use FedMix instead of NaiveMixMAFL · CIFAR10test accuracy: 77.4 -> 81.2Improved
Use FedMix instead of NaiveMixMAFL · Shakespearetest accuracy: 56.9 -> 56.9No clear effect
Approximate global Mixup with FedMix rather than perform Global MixupCIFAR10 federated learning · CIFAR10test accuracy: 88.2 -> 81.2Hurt
Use FedMix when clients have data from only 2 classes instead of 10Federated learning · CIFAR10test accuracy: 89.1; 81.2Mixed
Use FedMix with partial participation (K/N=0.1) instead of full participation (K/N=1.0)Federated learning · CIFAR10test accuracy: 84.3 -> 74.7Hurt
Use larger mixup ratio λ=0.5 rather than λ=0.05 (ablation)FedMix · CIFAR10test accuracy: 81.2 -> 67.1Hurt
Use same-class split rather than random split for averaging (ablation)FedMix · CIFAR10test accuracy: 81.2 -> 78.8Hurt

Later papers that compared with this method

3 later accepted papers report FedMix as a baseline in their results tables; 3 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