AI Paper Atlas

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

Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning

Junyi Li, Heng Huang

NeurIPS 2023 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 0 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
FedSep adaptive sub-model extraction instead of FedRolex rolling extractionResNet-18 model-heterogeneous FL · CIFAR-100 high heterogeneitytest accuracy (%): 56.57 -> 58.16Improved
FedSep instead of FedRolexResNet-18 model-heterogeneous FL · CIFAR-100 low heterogeneitytest accuracy (%): 58.73 -> 61.41Improved
FedSep instead of FedRolexResNet-18 model-heterogeneous FL · CIFAR-10 high heterogeneitytest accuracy (%): 69.44 -> 71.13Improved
FedSep instead of FedRolexResNet-18 model-heterogeneous FL · CIFAR-10 low heterogeneitytest accuracy (%): 84.45 -> 84.61No clear effect
FedSep instead of FlashResNet-18 model-heterogeneous FL · CIFAR-10 low heterogeneitytest accuracy (%): 84.61 -> 84.61No clear effect
FedSep (data-dependent mask) instead of HeteroFL fixed extractionResNet-18 model-heterogeneous FL · CIFAR-10 low heterogeneitytest accuracy (%): 73.19 -> 84.61Improved
FedSep instead of FedDSTResNet-18 model-heterogeneous FL · CIFAR-100 low heterogeneitytest accuracy (%): 54.97 -> 61.41Improved
FedSep (no public data) instead of KD-based Fed-ETResNet-18 model-heterogeneous FL · CIFAR-10 high heterogeneitytest accuracy (%): 78.66 -> 71.13Hurt
FedSep instead of KD-based Fed-ETResNet-18 model-heterogeneous FL · CIFAR-100 high heterogeneitytest accuracy (%): 35.78 -> 58.16Improved
FedSep instead of KD-based Fed-ETResNet-18 model-heterogeneous FL · CIFAR-10 low heterogeneitytest accuracy (%): 81.13 -> 84.61Improved
FedSep instead of Federated DropoutResNet-18 model-heterogeneous FL · CIFAR-10 high heterogeneitytest accuracy (%): 46.64 -> 71.13Improved
Heterogeneous submodels with FedSep versus homogeneous largest modelResNet-18 FedSep · CIFAR-100 high heterogeneitytest accuracy (%): 60.89 -> 58.16Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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