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 141–150 of 311 papers

TitleStatusHype
How to Backdoor HyperNetwork in Personalized Federated Learning?—0
Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data—0
Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks—0
Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning—0
Integrating Personalized Federated Learning with Control Systems for Enhanced Performance—0
Lower Bounds and Optimal Algorithms for Personalized Federated Learning—0
Influence-oriented Personalized Federated Learning—0
Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning—0
Robustness and Personalization in Federated Learning: A Unified Approach via Regularization—0
Client-supervised Federated Learning: Towards One-model-for-all Personalization—0
Show:102550
← PrevPage 15 of 32Next →

No leaderboard results yet.