手法を比較

	正則化転移学習	距離学習
分野	機械学習	機械学習
系統	Machine learning	Machine learning
提唱年	2000s–2010s	2003 (foundational); refined 2009 (LMNN)
提唱者	Pan, S. J. & Yang, Q. (survey); regularization variants by multiple authors	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.
種類	Regularized supervised/semi-supervised learning framework	Representation learning / supervised distance optimization
原典	Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.	Xing, E. P., Jordan, M. I., Russell, S., & Ng, A. Y. (2003). Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems (NIPS), 16, 505–512.
別名	regularized domain adaptation, transfer learning with regularization, penalized transfer learning, regularized fine-tuning	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance
関連	6	5
概要	Regularized Transfer Learning applies explicit penalty terms to a transfer learning pipeline to control how much a model shifts away from source-domain knowledge when adapting to a new target domain. The regularizer discourages negative transfer — the harmful carry-over of irrelevant source patterns — while preserving beneficial shared representations and preventing overfitting when target-domain labels are scarce.	Metric learning is a machine-learning framework that trains a distance or similarity function from data so that semantically similar examples end up close together in the learned space while dissimilar examples are pushed apart. Unlike fixed distances such as Euclidean, the learned metric adapts to the structure of the task, making downstream classifiers, clusterers, and retrieval systems significantly more accurate.