手法を比較

	アンサンブル転移学習	ブースティング
分野	機械学習	機械学習
系統	Machine learning	Machine learning
提唱年	2010s	1990–1997
提唱者	Various (consolidated in deep learning era, 2010s)	Schapire, R. E.; Freund, Y.
種類	Ensemble of pre-trained / fine-tuned models	Sequential ensemble (iterative reweighting)
原典	Ganaie, M. A., Hu, M., Malik, A. K., Tanveer, M., & Suganthan, P. N. (2022). Ensemble deep learning: A review. Engineering Applications of Artificial Intelligence, 115, 105151.	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.
別名	transfer ensemble, multi-model transfer learning, ensemble of fine-tuned models, ETL	AdaBoost, gradient boosting, iterative reweighting ensemble, sequential ensemble
関連	6	6
概要	Ensemble Transfer Learning combines multiple models that were each pre-trained on a large source domain and then fine-tuned on a target task. By aggregating the predictions of several independently fine-tuned models, it achieves higher accuracy and robustness than any single transferred model alone, especially when the target dataset is small.	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.