AI Paper Atlas

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

A Bayesian Federated Learning Framework With Online Laplace Approximation

Liangxi Liu, Xi Jiang, Feng Zheng, Hong Chen, Guo-Jun Qi, Heng Huang, Ling Shao

TPAMI 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 80 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 multivariate Gaussian product aggregation with prior-loss local training instead of FedAvgFedAvg · CIFAR-10 CNN, alpha=0.01, N=20global accuracy: 42.16% -> 48.57%Improved
use FOLA instead of FedAvg for convergence speedFedAvg · CIFAR-10 CNN, alpha=0.01, N=20rounds to reach 30% GA: 23 -> 4 rounds to 30% GAImproved
use FOLA instead of FedAvg for convergence speed to 40% GAFedAvg · CIFAR-10 CNN, alpha=0.01, N=20rounds to reach 40% GA: 73 -> 21 roundsImproved
use FedCurv instead of FedAvg (indirect AE reduction)FedAvg · CIFAR-10 CNN, alpha=0.01, N=20global accuracy: 42.16% -> 41.31%No clear effect
use FedNova under extreme heterogeneityFedAvg · CIFAR-10 CNN, alpha=0.01, N=20global accuracy: 42.16% -> 10.00%Hurt
use SCAFFOLD under extreme heterogeneityFedAvg · CIFAR-10 CNN, alpha=0.01, N=20global accuracy: 42.16% -> 20.30%Hurt
use online Laplace approximation instead of offline (ablation)FOLA aggregation · CIFAR-10 CNNglobal accuracyImproved
add Gaussian-product aggregation over FedAvg averaging (same local training) (ablation)FOLA · CIFAR-10 CNNglobal accuracyImproved
add both aggregation and local prior-loss strategies versus single module (ablation)FOLA · CIFAR-10 CNNglobal accuracyImproved
use full Laplace instead of diagonal Fisher covariance (ablation)FOLA aggregation · MNIST 780-10, 2 clientsglobal accuracy: nearly 90% GA in 3 rounds vs more than 10 roundsImproved
use e-full instead of diagonal Fisher covariance (ablation)FOLA aggregation · MNIST 780-10, 2 clientsglobal accuracyHurt
decrease data heterogeneity alpha (more heterogeneous) (ablation)FOLA vs FedAvg · MNIST MLPglobal accuracyHurt

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