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

by   Jianqing Zhang, et al.
Queen's University Belfast
Shanghai Jiao Tong University
Louisiana State University

Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization in FL. However, from the perspective of feature extraction, most existing pFL methods only focus on extracting global or personalized feature information during local training, which fails to meet the collaborative learning and personalization goals of pFL. To address this, we propose a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client. We conduct extensive experiments on six datasets in three statistically heterogeneous settings and show the superiority of GPFL over ten state-of-the-art methods regarding effectiveness, scalability, fairness, stability, and privacy. Besides, GPFL mitigates overfitting and outperforms the baselines by up to 8.99


page 1

page 2

page 3

page 4


FedALA: Adaptive Local Aggregation for Personalized Federated Learning

A key challenge in federated learning (FL) is the statistical heterogene...

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

Recently, personalized federated learning (pFL) has attracted increasing...

Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application

Federated learning (FL) shines through in the internet of things (IoT) w...

Personalized Federated Learning with Hidden Information on Personalized Prior

Federated learning (FL for simplification) is a distributed machine lear...

A Closer Look at Personalization in Federated Image Classification

Federated Learning (FL) is developed to learn a single global model acro...

A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacy

A distinguishing characteristic of federated learning is that the (local...

Cross-Fusion Rule for Personalized Federated Learning

Data scarcity and heterogeneity pose significant performance challenges ...

Please sign up or login with your details

Forgot password? Click here to reset