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 261–270 of 311 papers

TitleStatusHype
Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated LearningCode0
TPFL: Tsetlin-Personalized Federated Learning with Confidence-Based ClusteringCode0
pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated LearningCode0
Decentralized Personalized Federated Learning based on a Conditional Sparse-to-Sparser SchemeCode0
Private Multi-Task Learning: Formulation and Applications to Federated LearningCode0
Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated LearningCode0
Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic SurgeryCode0
Motley: Benchmarking Heterogeneity and Personalization in Federated LearningCode0
Provably Personalized and Robust Federated LearningCode0
Federated Face Forgery Detection Learning with Personalized RepresentationCode0
Show:102550
← PrevPage 27 of 32Next →

No leaderboard results yet.