Comparer des méthodes

	Apprentissage Actif Fédéré	Apprentissage semi-supervisé
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2020s	1970s–2006 (formalized)
Auteur d'origine	Multiple authors (federated active learning emerged ~2020)	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
Type	Hybrid paradigm (active querying within distributed training)	Learning paradigm
Source fondatrice	Ro, J. Y., Ali, A., Lin, Z., & Suresh, A. T. (2021). Scaling Federated Learning for Fine-tuning of Large Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP).	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9
Alias	Federated Active Learning, FAL, Active Federated Learning, distributed active learning	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
Apparentées	6	5
Résumé	Federated Active Learning combines the annotation-efficiency of active learning with the privacy-preserving decentralization of federated learning. A shared global model is trained across distributed clients, each of which independently ranks its unlabeled local data and requests labels only for the most informative examples, keeping raw data on-device throughout.	Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained.