mlsanityData to 14 Oct 2026

Federated Learning with Positive and Unlabeled Data

arXiv 2106.10904 ↗First posted 21 Jun 2021cs.LGcited by 10

Not on the map. Why?

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

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

14 of 35 references.

References · 14

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  6. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  8. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  9. 2019Federated Machine Learning: Concept and Applicationscited by 412
  10. 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 219
  11. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  12. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
2 more
  1. 2020Federated Learning with Only Positive Labelscited by 55
  2. 2020Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Modelscited by 10

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 7; 2024: 2.

10 papers.

  1. 2021Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfercited by 23
  2. 2023A Survey for Federated Learning Evaluations: Goals and Measurescited by 16
  3. 2023Federated Learning without Full Labels: A Surveycited by 13
  4. 2024A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applicationscited by 8
  5. 2023Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Frameworkcited by 6
  6. 2024Lightweight Unsupervised Federated Learning with Pretrained Vision Language Modelcited by 5
  7. 2023Local or Global: Selective Knowledge Assimilation for Federated Learning with Limited Labelscited by 4
  8. 2023Scale Federated Learning for Label Set Mismatch in Medical Image Classificationcited by 3
  9. 2023Regression with Sensor Data Containing Incomplete Observationscited by 0
  10. 2023Federated Split Learning with Only Positive Labels for resource-constrained IoT environmentcited by 0