Federated Learning with Positive and Unlabeled Data

Abstract

We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time. Different from the settings in traditional PU learning where the negative class consists of a single class, the negative samples which cannot be identified by a client in the federated setting may come from multiple classes which are unknown to the client. Therefore, existing PU learning methods can be hardly applied in this situation. To address this problem, we propose a novel framework, namely Federated learning with Positive and Unlabeled data (FedPU), to minimize the expected risk of multiple negative classes by leveraging the labeled data in other clients. We theoretically analyze the generalization bound of the proposed FedPU. Empirical experiments show that the FedPU can achieve much better performance than conventional supervised and semi-supervised federated learning methods. Code is available at https://github.com/littleSunlxy/FedPU-torch

References in corpus (4)

• Differentially Private Federated Learning: A Client Level Perspective
• Federated Optimization in Heterogeneous Networks
• Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data
• Positive-Unlabeled Learning with Non-Negative Risk Estimator

Cited by in corpus (1)

• Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer