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 301–311 of 311 papers

TitleStatusHype
Personalized Federated Learning with First Order Model OptimizationCode1
FedHome: Cloud-Edge based Personalized Federated Learning for In-Home Health MonitoringCode0
Ditto: Fair and Robust Federated Learning Through PersonalizationCode1
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning ApproachCode0
Lower Bounds and Optimal Algorithms for Personalized Federated Learning—0
Intrusion Detection with Segmented Federated Learning for Large-Scale Multiple LANsCode1
Robustness and Personalization in Federated Learning: A Unified Approach via Regularization—0
Personalized Federated Learning with Moreau EnvelopesCode1
Adaptive Personalized Federated LearningCode2
Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework—0
Personalized Federated Learning: A Meta-Learning Approach—0
Show:102550
← PrevPage 7 of 7Next →

No leaderboard results yet.