AI Paper Atlas

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

Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity Matching

Wonyong Jeong, Sung Ju Hwang

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Personalization with global-local trade-off · 4 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
aggregate all parameters (beta) instead of only basis vectors (alpha)Factorized-FL · CIFAR-10 Standard Non-IIDaccuracy %: 50.34 -> 65.30Improved
beta vs alpha on domain-heterogeneous averageFactorized-FL · domain & label heterogeneousaccuracy %: 64.49 -> 63.93Hurt
beta vs alpha communication cost, domain-heterogeneousFactorized-FL · domain & label heterogeneouscost Gb: 0.64 -> 36.5Hurt
permute labels across clientsFedAvg · CIFAR-10 Standard IIDaccuracy %: 70.28 -> 65.31Hurt
permute labels across clientsFactorized-FL alpha · CIFAR-10 IIDaccuracy %: 66.97 -> 67.91No clear effect
naive aggregation in domain-heterogeneous settingFedAvg vs Stand-Alone · domain & label heterogeneousaccuracy %: 61.35 -> 56.42Hurt
kernel factorization (Factorized-FedAvg vs FedAvg) (ablation)FedAvg · domain-heterogeneousaccuracyImproved
remove sparse bias matrix M (ablation)Factorized-FedAvg · domain-heterogeneousaccuracyHurt
factorize u in R^{F.F}, v in R^{I.O} instead of u in R^{I.F}, v in R^{O.F} (ablation)Factorized-FL · domain-heterogeneousaccuracyImproved
random or worst matching instead of similarity matching (ablation)Factorized-FL · multi-domainaccuracyHurt
increase gamma (rank)Factorized-FL · domain-heterogeneousaccuracyHurt
lower similarity threshold tauFactorized-FL · domain-heterogeneousaccuracyHurt

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