Compara mètodes

	Aprenentatge Actiu i Aprenentatge Federat	Aprenentatge autosupervisat
Camp	Aprenentatge automàtic	Aprenentatge automàtic
Família	Machine learning	Machine learning
Any d'origen	2020s	2018–2020
Autor original	Multiple authors (federated active learning emerged ~2020)	LeCun, Y. and community (formalized ~2018–2020)
Tipus	Hybrid paradigm (active querying within distributed training)	Representation learning paradigm
Font seminal	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).	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
Àlies	Federated Active Learning, FAL, Active Federated Learning, distributed active learning	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Relacionats	6	3
Resum	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.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.