AI Paper Atlas

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

A Random Projection Approach to Personalized Federated Learning: Enhancing Communication Efficiency, Robustness, and Fairness

Yuze Han, Xiang Li, Shiyun Lin, Zhihua Zhang

JMLR 2024 · Federated learning and privacy › Communication-efficient FL · approach: Local drift correction

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 random subspace projection with L1 regularization (lp-proj-1) instead of FedAvgpersonalized FL · ImageNet ResNet34test accuracy: 0.0458 (0.0004) -> 0.8403 (0.0071)Improved
use random projection (lp-proj-1) instead of pFedMepersonalized FL · ImageNet ResNet34communication bytes: 2.582 × 1011 -> 1.2 × 107Improved
use lp-proj-1 instead of pFedMepersonalized FL · ImageNet ResNet34test accuracy: 0.5009 (0.0130) -> 0.8403 (0.0071)Improved
use lp-proj-1 instead of LBGMpersonalized compressed FL · Synthetic(0, 0) target accuracy 0.6bytes used: 12200 -> 4620Improved
use lp-proj-1 instead of FedAvg under byte budgetpersonalized FL · Synthetic(0, 0), 328020 bytes budgettest accuracy: 0.625 -> 0.885Improved
use lp-proj-1 instead of best competing methodpersonalized FL · EMNIST target accuracy 0.7communication bytes: 79x and 1320xImproved
use lp-proj instead of other methods under same-value and Gaussian attacksrobust FL · EMNIST/Synthetic Byzantine attacksbenign client test accuracyImproved
use lp-proj-1 under sign-flipping attack with more than 20% malicious clientsrobust FL · sign-flipping attackbenign client test accuracyImproved
use lp-proj-1 instead of RSAfair FL · CIFARtest accuracy (%): 77.68 -> 79.22Improved
use lp-proj-2 instead of Dittofair FL · EMNISTtest accuracy (%): 90.89 -> 90.70No clear effect
use lp-proj instead of Dittopersonalized FL · EMNIST test accuracy curvestest accuracyNo clear effect
add block-diagonal projection with 50 blockslp-proj · ImageNet ResNet34space and computation complexityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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