AI Paper Atlas

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

Towards Personalized Federated Learning via Heterogeneous Model Reassembly

Jiaqi Wang, Xingyi Yang, Suhan Cui, Liwei Che, Lingjuan Lyu, Dongkuan Xu, Fenglong Ma

NeurIPS 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Bayesian personalized FL · 13 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 pFedHR instead of best baseline (FedGH) with labeled public dataheterogeneous FL · SVHN Non-IIDaccuracy: 81.06% -> 83.40%Improved
use pFedHR instead of FCCL with unlabeled public dataheterogeneous FL · CIFAR-10 IIDaccuracy: 68.77% -> 69.38%Improved
use pFedHR instead of FedMD with 100 clientsheterogeneous FL · SVHN Non-IID, N=100accuracy: 74.34% -> 77.63%Improved
use pFedHR with homogeneous clients vs best personalized baseline, simple model M1homogeneous FL · CIFAR-10 IIDaccuracy: 46.12% -> 54.38%Improved
use pFedHR with homogeneous clients on MNISThomogeneous FL · MNIST IID, M4accuracy: 95.77% -> 94.88%Hurt
use labeled instead of unlabeled public data (ablation)pFedHR · CIFAR-10 IIDaccuracy: 69.38% -> 73.88%Improved
increase number of stitching linear layers from 1 to 3 (ablation)pFedHR · SVHN, 12 clientsaccuracyHurt
increase server finetuning epochs of stitched model (ablation)pFedHR · SVHN, 12 clientsaccuracyHurt
increase percentage of public data from 2% to 5% to 10% (ablation)pFedHR · SVHNaccuracyImproved
increase number of clusters K (ablation)pFedHR · SVHN, 12 clientsaccuracyImproved
use different-distribution public data instead of SVHN public data (ablation)pFedHR and baselines · SVHNaccuracyHurt

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