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 291300 of 311 papers

TitleStatusHype
Personalized Federated Learning by Structured and Unstructured Pruning under Data HeterogeneityCode1
Personalized Federated Learning using HypernetworksCode1
A Theorem of the Alternative for Personalized Federated Learning0
Towards Personalized Federated Learning0
Personalized Federated Learning: A Unified Framework and Universal Optimization TechniquesCode0
Exploiting Shared Representations for Personalized Federated LearningCode1
A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian RegularizationCode1
On Data Efficiency of Meta-learning0
PFL-MoE: Personalized Federated Learning Based on Mixture of ExpertsCode1
Adaptive Intrusion Detection in the Networking of Large-Scale LANs with Segmented Federated LearningCode1
Show:102550
← PrevPage 30 of 32Next →

No leaderboard results yet.