# Federated Learning with Positive and Unlabeled Data

arXiv: https://arxiv.org/abs/2106.10904 · HTML: https://mlsanity.com/paper/2106.10904/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 21 Jun 2021.

## Builds on (most cited first, 14 of 14)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data](https://mlsanity.com/paper/2008.06180/) (2020)
- [Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning](https://mlsanity.com/paper/2006.12097/) (2020)
- [Federated Learning with Only Positive Labels](https://mlsanity.com/paper/2004.10342/) (2020)
- [Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models](https://mlsanity.com/paper/2008.11364/) (2020)

## Built on by (most cited first, 10 of 10)

- [Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer](https://mlsanity.com/paper/2109.08119/) (2021)
- [A Survey for Federated Learning Evaluations: Goals and Measures](https://mlsanity.com/paper/2308.11841/) (2023)
- [Federated Learning without Full Labels: A Survey](https://mlsanity.com/paper/2303.14453/) (2023)
- [A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications](https://mlsanity.com/paper/2403.01387/) (2024)
- [Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework](https://mlsanity.com/paper/2301.00489/) (2023)
- [Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model](https://mlsanity.com/paper/2404.11046/) (2024)
- [Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labels](https://mlsanity.com/paper/2307.08809/) (2023)
- [Scale Federated Learning for Label Set Mismatch in Medical Image Classification](https://mlsanity.com/paper/2304.06931/) (2023)
- [Regression with Sensor Data Containing Incomplete Observations](https://mlsanity.com/paper/2304.13415/) (2023)
- [Federated Split Learning with Only Positive Labels for resource-constrained IoT environment](https://mlsanity.com/paper/2307.13266/) (2023)

## Abstract (arXiv)

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