Federated Learning with Positive and Unlabeled Data
This addresses the challenge of limited labeled data in federated learning for applications like healthcare or IoT, representing an incremental improvement by adapting PU learning to federated multi-class scenarios.
The paper tackles the problem of learning from positive and unlabeled data in federated settings where negative samples may come from multiple unknown classes, proposing FedPU to minimize expected risk by leveraging labeled data across clients. Empirical results show FedPU achieves much better performance than conventional supervised and semi-supervised federated learning methods.
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