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

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

Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones, etc. Most existing pFL methods focus on exploiting the global information and personalized information in the client-level model parameters while neglecting that data is the source of these two kinds of information. To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively. FedCP is more fine-grained to consider personalization in a sample-specific manner than existing pFL methods. Extensive experiments in computer vision and natural language processing domains show that FedCP outperforms eleven state-of-the-art methods by up to 6.69 accidentally drop out, which frequently happens in mobile settings. Our code is public at https://github.com/TsingZ0/FedCP.


page 5

page 13


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

Federated Learning (FL) is popular for its privacy-preserving and collab...

Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation

Personalized Federated Learning (PFL) aims to learn personalized models ...

Personalized Federated Learning with Feature Alignment and Classifier Collaboration

Data heterogeneity is one of the most challenging issues in federated le...

Federated Natural Language Generation for Personalized Dialogue System

Neural conversational models have long suffered from the problem of inco...

Hypernetwork-based Personalized Federated Learning for Multi-Institutional CT Imaging

Computed tomography (CT) is of great importance in clinical practice due...

Federated Distillation of Natural Language Understanding with Confident Sinkhorns

Enhancing the user experience is an essential task for application servi...

Fusion of Global and Local Knowledge for Personalized Federated Learning

Personalized federated learning, as a variant of federated learning, tra...

Please sign up or login with your details

Forgot password? Click here to reset