AI Paper Atlas

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

Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization

Yan Sun, Li Shen, Dacheng Tao

NeurIPS 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 3 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
add relaxed initialization (beta=0.1) to FedAvg, i.e. FedInitFedAvg · CIFAR-10 ResNet-18-GN Dir-0.1 10%-100test accuracy (%): 72.53 -> 75.95Improved
reduce participation from 10% to 5% clientsFedInit · CIFAR-10 ResNet-18-GN Dir-0.1test accuracy (%): 75.95 -> 74.92No clear effect
reduce participation from 10% to 5% clientsFedAvg · CIFAR-10 ResNet-18-GN Dir-0.1test accuracy (%): 72.53 -> 70.65Hurt
add relaxed initialization to FedAdam (ablation)FedAdam · CIFAR-10 ResNet-18-GN 10%-100 Dir-0.6test accuracy (%): 76.52 -> 78.33Improved
add relaxed initialization to FedSAM (ablation)FedSAM · CIFAR-10 ResNet-18-GN 10%-100 Dir-0.6test accuracy (%): 79.23 -> 83.36Improved
add relaxed initialization to SCAFFOLD (ablation)SCAFFOLD · CIFAR-10 ResNet-18-GN 10%-100 Dir-0.1test accuracy (%): 75.06 -> 77.30Improved
add relaxed initialization to FedDyn (ablation)FedDyn · CIFAR-10 ResNet-18-GN 10%-100 Dir-0.6test accuracy (%): 82.43 -> 81.91No clear effect
add relaxed initialization to FedCM (ablation)FedCM · CIFAR-10 ResNet-18-GN 10%-100 Dir-0.1test accuracy (%): 73.93 -> 73.71No clear effect
negative beta (-0.2) instead of beta=0 (ablation)FedInit · CIFAR-10 ResNet-18-GN Dir-0.1 10%-100test accuracy (%): 72.53 -> 64.70Hurt
beta 0.1 instead of 0 (ablation)FedInit · CIFAR-10 ResNet-18-GN Dir-0.1 10%-100test accuracy (%): 72.53 -> 75.95Improved
beta 0.15 (too large) instead of 0.1 (ablation)FedInit · CIFAR-10 ResNet-18-GN Dir-0.1 10%-100test accuracy (%): 75.95 -> 44.47Hurt
increase local interval K (ablation)FedInit · CIFAR-10test accuracy (%)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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