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 281290 of 311 papers

TitleStatusHype
FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant ClientsCode0
Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax GuaranteesCode0
FedDWA: Personalized Federated Learning with Dynamic Weight AdjustmentCode0
Straggler-Resilient Personalized Federated LearningCode0
Personalization Improves Privacy-Accuracy Tradeoffs in Federated LearningCode0
Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data HeterogeneityCode0
Personalized Federated Learning with Contextual Modulation and Meta-LearningCode0
An Equivalence Between Data Poisoning and Byzantine Gradient AttacksCode0
DAMe: Personalized Federated Social Event Detection with Dual Aggregation MechanismCode0
Personalized Federated Learning: A Unified Framework and Universal Optimization TechniquesCode0
Show:102550
← PrevPage 29 of 32Next →

No leaderboard results yet.