AI Paper Atlas

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

ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients

Fatih Ilhan, Gong Su, Ling Liu

CVPR 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 95 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 ScaleFL's resource-adaptive width-and-depth splitting with early exits and self-distillation instead of FedDFResNet110 federated training · CIFAR-10 (α=100)global accuracy: 84.44 -> 85.53Improved
Use ScaleFL instead of HeteroFLResNet110 federated training · CIFAR-10 (α=1)global accuracy: 79.91 -> 80.83Improved
Use ScaleFL instead of HeteroFLResNet110 federated training · CIFAR-100 (α=100)global accuracy: 47.12 -> 49.94Improved
Use ScaleFL instead of FedDFResNet110 federated training · CIFAR-100 (α=1)global accuracy: 44.50 -> 44.95Improved
Use ScaleFL instead of HeteroFLMSDNet24 federated training · CIFAR-10 (α=100)global accuracy: 83.02 -> 84.77Improved
Use ScaleFL instead of HeteroFLMSDNet24 federated training · CIFAR-100 (α=1)global accuracy: 43.00 -> 46.12Improved
Use ScaleFL instead of HeteroFLEfficientNet-B4 federated training · ImageNet (α=100)global accuracy: 46.61 -> 48.95Improved
Use ScaleFL instead of HeteroFLEfficientNet-B4 federated training · ImageNet (α=1)global accuracy: 43.59 -> 46.78Improved
Use ScaleFL instead of the strongest listed baselineBERT federated training · SST-2 (α=100)global accuracy: 88.95 -> 88.58Hurt
Use ScaleFL instead of FedDFBERT federated training · SST-2 (α=1)global accuracy: 82.95 -> 83.79Improved
Use ScaleFL instead of HeteroFLBERT federated training · AgNews (α=100)global accuracy: 91.51 -> 92.13Improved
Use ScaleFL instead of HeteroFLBERT federated training · AgNews (α=1)global accuracy: 90.85 -> 91.20Improved

Later papers that compared with this method

2 later accepted papers report ScaleFL as a baseline in their results tables; 2 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