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 271–280 of 311 papers

TitleStatusHype
On Heterogeneously Distributed Data, Sparsity Matters—0
Agnostic Personalized Federated Learning with Kernel Factorization—0
Robust and Personalized Federated Learning with Spurious Features: an Adversarial Approach—0
Inference-Time Personalized Federated Learning—0
Towards Generalizable Personalized Federated Learning with Adaptive Local Adaptation—0
Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer—0
Connecting Low-Loss Subspace for Personalized Federated LearningCode1
Private Multi-Task Learning: Formulation and Applications to Federated LearningCode0
Federated Multi-Task Learning under a Mixture of DistributionsCode1
Federated Asymptotics: a model to compare federated learning algorithms—0
Show:102550
← PrevPage 28 of 32Next →

No leaderboard results yet.