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 1120 of 311 papers

TitleStatusHype
Personalized Federated Learning via Feature Distribution AdaptationCode1
Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank DecompositionCode1
Personalized Federated Continual Learning via Multi-granularity PromptCode1
FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-TuningCode1
FedAS: Bridging Inconsistency in Personalized Federated LearningCode1
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated LearningCode1
Adaptive Test-Time Personalization for Federated LearningCode1
Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated LearningCode1
A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical DatasetsCode1
Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive CollaborationCode1
Show:102550
← PrevPage 2 of 32Next →

No leaderboard results yet.