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

Showing 101110 of 311 papers

TitleStatusHype
Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central ServerCode0
pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated LearningCode0
FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal TransportCode0
Low-Resource Machine Translation through the Lens of Personalized Federated LearningCode0
FedAH: Aggregated Head for Personalized Federated LearningCode0
FHBench: Towards Efficient and Personalized Federated Learning for Multimodal HealthcareCode0
Flow: Per-Instance Personalized Federated Learning Through Dynamic RoutingCode0
FedSPU: Personalized Federated Learning for Resource-constrained Devices with Stochastic Parameter UpdateCode0
An Equivalence Between Data Poisoning and Byzantine Gradient AttacksCode0
Fusion of Global and Local Knowledge for Personalized Federated LearningCode0
Show:102550
← PrevPage 11 of 32Next →

No leaderboard results yet.