Comparer des méthodes

	Empilement auto-supervisé	Apprentissage semi-supervisé
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	1992–2018	1970s–2006 (formalized)
Auteur d'origine	Wolpert, D. H. (stacking); self-supervised extension via modern SSL literature	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
Type	Ensemble meta-learning with self-supervised pretraining	Learning paradigm
Source fondatrice	Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241–259.	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9
Alias	SSL stacking, self-supervised stacked generalization, self-supervised meta-ensemble, SSL ensemble stacking	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
Apparentées	6	5
Résumé	Self-supervised Stacking Ensemble combines stacked generalization — the classic two-level ensemble architecture introduced by Wolpert (1992) — with self-supervised pretraining, allowing base models to learn rich representations from unlabeled data before being fine-tuned and stacked. This hybrid strategy is especially powerful when labeled examples are scarce but unlabeled data is plentiful.	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.