SOTAVerified

Personalized Federated Learning

The federated learning setup presents numerous challenges including data heterogeneity (differences in data distribution), device heterogeneity (in terms of computation capabilities, network connection, etc.), and communication efficiency. Especially data heterogeneity makes it hard to learn a single shared global model that applies to all clients. To overcome these issues, Personalized Federated Learning (PFL) aims to personalize the global model for each client in the federation.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 141–150 of 311 papers

TitleStatusHype
Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning—0
pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning—0
Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks—0
FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning—0
FedHome: Cloud-Edge based Personalized Federated Learning for In-Home Health Monitoring—0
Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updates—0
A Theorem of the Alternative for Personalized Federated Learning—0
Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond—0
Achieving Personalized Federated Learning with Sparse Local Models—0
FedGradNorm: Personalized Federated Gradient-Normalized Multi-Task Learning—0
Show:102550
← PrevPage 15 of 32Next →

No leaderboard results yet.