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 21–30 of 311 papers

TitleStatusHype
FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated LearningCode1
You Can Backdoor Personalized Federated LearningCode1
Personalized Federated Learning with Feature Alignment and Classifier CollaborationCode1
Confidence-aware Personalized Federated Learning via Variational Expectation MaximizationCode1
Efficient Personalized Federated Learning via Sparse Model-AdaptationCode1
Personalized Federated Learning under Mixture of DistributionsCode1
PerAda: Parameter-Efficient Federated Learning Personalization with Generalization GuaranteesCode1
Tackling Data Heterogeneity in Federated Learning with Class PrototypesCode1
FedALA: Adaptive Local Aggregation for Personalized Federated LearningCode1
FedTP: Federated Learning by Transformer PersonalizationCode1
Show:102550
← PrevPage 3 of 32Next →

No leaderboard results yet.