mlsanityData to 13 Oct 2026

Exploring the Possibility of TypiClust for Low-Budget Federated Active Learning

arXiv 2505.19404 ↗First posted 26 May 2025cs.LG cs.AI cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated Active Learning (FAL) seeks to reduce the burden of annotation under the realistic constraints of federated learning by leveraging Active Learning (AL). As FAL settings make it more expensive to obtain ground truth labels, FAL strategies that work well in low-budget regimes, where the amount of annotation is very limited, are needed. In this work, we investigate the effectiveness of TypiClust, a successful low-budget AL strategy, in low-budget FAL settings. Our empirical results show that TypiClust works well even in low-budget FAL settings contrasted with relatively low performances of other methods, although these settings present additional challenges, such as data heterogeneity, compared to AL. In addition, we show that FAL settings cause distribution shifts in terms of typicality, but TypiClust is not very vulnerable to the shifts. We also analyze the sensitivity of TypiClust to feature extraction methods, and it suggests a way to perform FAL even in limited data situations.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

20 of 29 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,857
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,915
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,430
  8. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,363
  9. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,378
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  11. 2021Model-Contrastive Federated Learningcited by 766
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 606
8 more
  1. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 430
  2. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 132
  3. 2022Active Learning by Feature Mixingcited by 63
  4. 2022Cross-Silo Federated Learning: Challenges and Opportunitiescited by 38
  5. 2023Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shiftscited by 28
  6. 2022Knowledge-Aware Federated Active Learning with Non-IID Datacited by 16
  7. 2023Re-thinking Federated Active Learning based on Inter-class Diversitycited by 14
  8. 2024SUPClust: Active Learning at the Boundariescited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Coordination on a Budget: Federated Active Learning with Few Labelscited by 0