Porovnat metody

	Ensemble Federated Learning	Zesilování	Stacking
Obor	Strojové učení	Strojové učení	Strojové učení
Rodina	Machine learning	Machine learning	Machine learning
Rok vzniku	2017–2019	1990–1997	1992
Tvůrce	McMahan et al. (FedAvg) extended by subsequent ensemble work	Schapire, R. E.; Freund, Y.	Wolpert, D.H.
Typ	Ensemble meta-strategy over federated clients	Sequential ensemble (iterative reweighting)	Ensemble (heterogeneous meta-learning)
Původní zdroj	McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 54, 1273–1282.	Freund, Y. & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139.	Wolpert, D.H. (1992). Stacked Generalization. Neural Networks, 5(2), 241–259.
Další názvy	federated ensemble learning, EFL, federated model ensembling, federated multi-model aggregation	AdaBoost, gradient boosting, iterative reweighting ensemble, sequential ensemble	Stacking (Yığınlama — Meta-Öğrenme), stacked generalization, meta-learning ensemble, super learner
Příbuzné	6	6	5
Shrnutí	Ensemble Federated Learning combines the privacy-preserving distribution of federated learning with ensemble aggregation: each participating client trains its own local model on private data, and the server aggregates predictions — or model parameters — from all clients using ensemble strategies such as voting, averaging, or stacking, instead of simple parameter averaging alone.	Boosting is a sequential ensemble technique that converts many simple, barely-better-than-chance learners into a single highly accurate model by repeatedly focusing training on the examples that previous learners got wrong, then combining all learners with weights proportional to their individual accuracy.	Stacking, or stacked generalization, is an ensemble method introduced by David Wolpert in 1992 that combines the outputs of several different base models (Level-0) through a separate meta-model (Level-1). Unlike bagging and boosting, it deliberately uses heterogeneous model types, and it is the standard final-stage strategy in Kaggle competitions.