AI Paper Atlas

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

ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training

Hui-Po Wang, Sebastian Stich, Yang He, Mario Fritz

ICML 2022 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 12 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
progressive training instead of end-to-end training in federated learningFedAvg, ResNet-18 · CIFAR-100 federatedaccuracy (%): 52.08 ± 0.44 -> 53.23 ± 0.09Improved
progressive training instead of end-to-end trainingFedAvg, ConvNet · EMNIST federatedaccuracy (%): 85.75 ± 0.11 -> 85.67 ± 0.06No clear effect
progressive training in centralized trainingResNet/VGG · CIFAR-100 centralizedaccuracy (%): 76.08±0.12 -> 75.84±0.28 (ResNet-18); 77.77±0.38 -> 78.57±0.33 (ResNet-152)No clear effect
symmetric growth (outer to inner) instead of asymmetric growth in U-net (ablation)ProgFed 3D-Unet · BraTS federatedcommunication cost change: -5.02% -> -63.60 %Improved
combine ProgFed with FedAdamProgFed · CIFAR-100 federatedaccuracy (%): 56.21 -> 60.55Improved
combine ProgFed with FedProxProgFed · EMNIST federatedaccuracy (%): 86.36 -> 86.08No clear effect
combine ProgFed with quantization (LQ-2)ResNet-18 federated · CIFAR-100 federatedaccuracy (%): 47.26 -> 52.87Improved
add warm-up for newly added layers (ablation)ProgFed · CIFAR-100 federated ResNet-18accuracy (%): 51.09 -> 53.23Improved
progressive training instead of layerwise training (ablation)ProgFed · CIFAR-100 centralized ResNet-18accuracy (%): 72.40±0.16 -> 75.84±0.28Improved
progressive growth instead of random sub-model selection (ablation)ProgFed · CIFAR-100 centralized ResNet-18accuracy (%): 74.38±0.97 -> 75.84±0.28Improved
progressive growth instead of partial update with final-head supervision (ablation)ProgFed · CIFAR-100 centralized ResNet-18accuracy (%): 74.70±0.04 -> 75.84±0.28Improved
combine local and final-head supervision (Mixed) vs local-head only (ablation)ProgFed · CIFAR-100 centralized ResNet-18accuracy (%): 75.84±0.28 -> 75.04±1.26Hurt

Later papers that compared with this method

1 later accepted paper reports ProgFed 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