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 11–20 of 311 papers

TitleStatusHype
Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data—0
Privacy-Preserving Personalized Federated Learning for Distributed Photovoltaic Disaggregation under Statistical Heterogeneity—0
DP2FL: Dual Prompt Personalized Federated Learning in Foundation Models—0
FHBench: Towards Efficient and Personalized Federated Learning for Multimodal HealthcareCode0
A Novel Algorithm for Personalized Federated Learning: Knowledge Distillation with Weighted Combination Loss—0
Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos—0
RCC-PFL: Robust Client Clustering under Noisy Labels in Personalized Federated Learning—0
pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learning—0
Semantic Communication in Dynamic Channel Scenarios: Collaborative Optimization of Dual-Pipeline Joint Source-Channel Coding and Personalized Federated Learning—0
Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updates—0
Show:102550
← PrevPage 2 of 32Next →

No leaderboard results yet.