mlsanityData to 7 Oct 2026

Re-thinking Federated Active Learning based on Inter-class Diversity

arXiv 2303.12317 ↗First posted 22 Mar 2023cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Although federated learning has made awe-inspiring advances, most studies have assumed that the client's data are fully labeled. However, in a real-world scenario, every client may have a significant amount of unlabeled instances. Among the various approaches to utilizing unlabeled data, a federated active learning framework has emerged as a promising solution. In the decentralized setting, there are two types of available query selector models, namely 'global' and 'local-only' models, but little literature discusses their performance dominance and its causes. In this work, we first demonstrate that the superiority of two selector models depends on the global and local inter-class diversity. Furthermore, we observe that the global and local-only models are the keys to resolving the imbalance of each side. Based on our findings, we propose LoGo, a FAL sampling strategy robust to varying local heterogeneity levels and global imbalance ratio, that integrates both models by two steps of active selection scheme. LoGo consistently outperforms six active learning strategies in the total number of 38 experimental settings.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 30 of its 53 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

30 of 53 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2018Federated Learning with Non-IID Datacited by 1,099
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2017Selective Classification for Deep Neural Networkscited by 799
  9. 2021Model-Contrastive Federated Learningcited by 762
  10. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
  11. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  12. 2020Federated Learning with Matched Averagingcited by 564
18 more
  1. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  2. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  3. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  4. 2019Variational Adversarial Active Learningcited by 284
  5. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  6. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
  7. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  8. 2020Contextual Diversity for Active Learningcited by 139
  9. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  10. 2017Deep Active Learning over the Long Tailcited by 82
  11. 2022Divergence-aware Federated Self-Supervised Learningcited by 71
  12. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  13. 2021Collaborative Unsupervised Visual Representation Learning from Decentralized Datacited by 68
  14. 2019Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applicationscited by 64
  15. 2022Active Learning by Feature Mixingcited by 63
  16. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  17. 2022Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learningcited by 13
  18. 2020Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classificationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 3; 2026: 3.

13 papers.

Sort:

By area:

  1. 2023Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shiftscited by 26
  2. 2024Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasetscited by 7
  3. 2023ActiveDC: Distribution Calibration for Active Finetuningcited by 3
  4. 2025FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Trainingcited by 2
  5. 2025Active Learning via Vision-Language Model Adaptation with Open Datacited by 2
  6. 2025Exploring the Possibility of TypiClust for Low-Budget Federated Active Learningcited by 1
  7. 2023Federated Active Learning for Target Domain Generalisationcited by 0
  8. 2024Differentially Private Active Learning: Balancing Effective Data Selection and Privacycited by 0
  9. 2024Multi-Label Bayesian Active Learning with Inter-Label Relationshipscited by 0
  10. 2024Federated Learning with Workload Reduction through Partial Training of Client Models and Entropy-Based Data Selectioncited by 0
  11. 2026Federated Active Learning Under Extreme Non-IID and Global Class Imbalancecited by 0
  12. 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregationcited by 0
1 more
  1. 2026Coordination on a Budget: Federated Active Learning with Few Labelscited by 0