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 251–260 of 311 papers

TitleStatusHype
Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated LearningCode0
Personalized Federated Learning with Communication Compression—0
Tensor Decomposition based Personalized Federated Learning—0
FedMCSA: Personalized Federated Learning via Model Components Self-Attention—0
Personalizing or Not: Dynamically Personalized Federated Learning with Incentives—0
Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning—0
Motley: Benchmarking Heterogeneity and Personalization in Federated LearningCode0
Adaptive Expert Models for Personalization in Federated LearningCode0
pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning—0
Group privacy for personalized federated learning—0
Show:102550
← PrevPage 26 of 32Next →

No leaderboard results yet.