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 2130 of 311 papers

TitleStatusHype
Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank DecompositionCode1
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse TrainingCode1
An Empirical Study of Personalized Federated LearningCode1
Efficient Split-Mix Federated Learning for On-Demand and In-Situ CustomizationCode1
FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-TuningCode1
FedALA: Adaptive Local Aggregation for Personalized Federated LearningCode1
Adaptive Intrusion Detection in the Networking of Large-Scale LANs with Segmented Federated LearningCode1
FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural NetworksCode1
Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive CollaborationCode1
Personalized Federated Learning with Adaptive Batchnorm for HealthcareCode1
Show:102550
← PrevPage 3 of 32Next →

No leaderboard results yet.