FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Haoyuan, Funk, Mathias, Wang, Jindong, Saeed, Aaqib
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910952696315904
author Li, Haoyuan
Funk, Mathias
Wang, Jindong
Saeed, Aaqib
author_facet Li, Haoyuan
Funk, Mathias
Wang, Jindong
Saeed, Aaqib
contents Federated Active Learning (FAL) has emerged as a promising framework to leverage large quantities of unlabeled data across distributed clients while preserving data privacy. However, real-world deployments remain limited by high annotation costs and communication-intensive sampling processes, particularly in a cross-silo setting, when clients possess substantial local datasets. This paper addresses the crucial question: What is the best practice to reduce communication costs in human-in-the-loop learning with minimal annotator effort? Existing FAL methods typically rely on iterative annotation processes that separate active sampling from federated updates, leading to multiple rounds of expensive communication and annotation. In response, we introduce FAST, a two-pass FAL framework that harnesses foundation models for weak labeling in a preliminary pass, followed by a refinement pass focused exclusively on the most uncertain samples. By leveraging representation knowledge from foundation models and integrating refinement steps into a streamlined workflow, FAST substantially reduces the overhead incurred by iterative active sampling. Extensive experiments on diverse medical and natural image benchmarks demonstrate that FAST outperforms existing FAL methods by an average of 4.36% while reducing communication rounds eightfold under a limited 5% labeling budget.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03783
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training
Li, Haoyuan
Funk, Mathias
Wang, Jindong
Saeed, Aaqib
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
Federated Active Learning (FAL) has emerged as a promising framework to leverage large quantities of unlabeled data across distributed clients while preserving data privacy. However, real-world deployments remain limited by high annotation costs and communication-intensive sampling processes, particularly in a cross-silo setting, when clients possess substantial local datasets. This paper addresses the crucial question: What is the best practice to reduce communication costs in human-in-the-loop learning with minimal annotator effort? Existing FAL methods typically rely on iterative annotation processes that separate active sampling from federated updates, leading to multiple rounds of expensive communication and annotation. In response, we introduce FAST, a two-pass FAL framework that harnesses foundation models for weak labeling in a preliminary pass, followed by a refinement pass focused exclusively on the most uncertain samples. By leveraging representation knowledge from foundation models and integrating refinement steps into a streamlined workflow, FAST substantially reduces the overhead incurred by iterative active sampling. Extensive experiments on diverse medical and natural image benchmarks demonstrate that FAST outperforms existing FAL methods by an average of 4.36% while reducing communication rounds eightfold under a limited 5% labeling budget.
title FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2504.03783