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.

Personalized Federated Learning

Benchmarks

Libraries

Datasets

Subtasks

Most implemented papers

Adaptive Personalized Federated Learning

Content

Personalized Federated Learning with Moreau Envelopes

Ditto: Fair and Robust Federated Learning Through Personalization

Federated Multi-Task Learning under a Mixture of Distributions

Exploiting Shared Representations for Personalized Federated Learning

Personalized Federated Learning with First Order Model Optimization

FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy

GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning

Personalized Federated Learning with Feature Alignment and Classifier Collaboration