mlsanityData to 7 Oct 2026

Federated Active Learning for Target Domain Generalisation

arXiv 2312.02247 ↗First posted 4 Dec 2023cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce Active Learning framework in Federated Learning for Target Domain Generalisation, harnessing the strength from both learning paradigms. Our framework, FEDALV, composed of Active Learning (AL) and Federated Domain Generalisation (FDG), enables generalisation of an image classification model trained from limited source domain client's data without sharing images to an unseen target domain. To this end, our FDG, FEDA, consists of two optimisation updates during training, one at the client and another at the server level. For the client, the introduced losses aim to reduce feature complexity and condition alignment, while in the server, the regularisation limits free energy biases between source and target obtained by the global model. The remaining component of FEDAL is AL with variable budgets, which queries the server to retrieve and sample the most informative local data for the targeted client. We performed multiple experiments on FDG w/ and w/o AL and compared with both conventional FDG baselines and Federated Active Learning baselines. Our extensive quantitative experiments demonstrate the superiority of our method in accuracy and efficiency compared to the multiple contemporary methods. FEDALV manages to obtain the performance of the full training target accuracy while sampling as little as 5% of the source client's data.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

32 of 48 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  6. 2018Federated Learning with Non-IID Datacited by 1,099
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  8. 2017Deep Bayesian Active Learning with Image Datacited by 812
  9. 2021Model-Contrastive Federated Learningcited by 762
  10. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  11. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  12. 2020A Survey of Deep Active Learningcited by 547
20 more
  1. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  2. 2019Learning Loss for Active Learningcited by 335
  3. 2019Variational Adversarial Active Learningcited by 284
  4. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  5. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  6. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  7. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  8. 2021Deep Federated Learning for Autonomous Drivingcited by 54
  9. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  10. 2020Training Speech Recognition Models with Federated Learning: A Quality/Cost Frameworkcited by 46
  11. 2018Multi-component Image Translation for Deep Domain Generalizationcited by 40
  12. 2022Context-Aware Robust Fine-Tuningcited by 27
  13. 2023Federated Domain Generalization: A Surveycited by 25
  14. 2023StableFDG: Style and Attention Based Learning for Federated Domain Generalizationcited by 21
  15. 2022Improving Federated Learning Face Recognition via Privacy-Agnostic Clusterscited by 18
  16. 2020Impact of ImageNet Model Selection on Domain Adaptationcited by 15
  17. 2022Knowledge-Aware Federated Active Learning with Non-IID Datacited by 15
  18. 2020Active Learning for Bayesian 3D Hand Pose Estimationcited by 13
  19. 2022Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learningcited by 13
  20. 2023Re-thinking Federated Active Learning based on Inter-class Diversitycited by 13

Built on by

Not cited yet.