Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.19404 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912717938360320 |
|---|---|
| author | Ono, Yuta Nakamura, Hiroshi Takase, Hideki |
| author_facet | Ono, Yuta Nakamura, Hiroshi Takase, Hideki |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19404 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring the Possibility of TypiClust for Low-Budget Federated Active Learning Ono, Yuta Nakamura, Hiroshi Takase, Hideki Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | Exploring the Possibility of TypiClust for Low-Budget Federated Active Learning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.19404 |