Abstract
We describe different scenarios where a learning mechanism is capable of acquiring experience on a source task, and subsequently exploit such experience on a target task. The core ideas behind this ability to transfer knowledge from one task to another have been studied in the machine learning literature under different titles and perspectives. Here we describe some of them under the names of inductive transfer, transfer learning, multitask learning, meta-searching, meta-generalization, and domain adaptation.
This is a preview of subscription content, log in via an institution to check access.
Recommended Reading
Baxter J (2000) A model of inductive learning bias. J Artif Intell Res 12:149–198
Ben-David S, Blitzer J, Crammer K, Pereira F (2007) Analysis of representations for domain adaptation. Adv Neural Inf Process Syst 19:137–144
Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Wortman J (2010) A theory of learning from different domains. Mach Learn Spec Issue Learn Mult Sources 79:151–175
Brazdil P, Giraud-Carrier C, Soares C, Vilalta R (2009) Metalearning: applications to data mining. Springer, Berlin
Caruana R (1993) Multitask learning: a knowledge-based source of inductive bias. In: Proceedings of the 10th international conference on machine learning (ICML), Amherst, pp 41-48
Chen M, Weinberger KQ, Blitzer J (2011) Co-training for domain adaptation. In: Advances in neural information processing systems (NIPS), Granada
Dai W, Yang Q, Xue G, Yu Y (2007) Boosting for transfer learning. In: Proceedings of the 24th international conference on machine learning (ICML), Corvallis, pp 193–200
Daumé H, Marcu D (2006) Domain adaptation for statistical classifiers. J Mach Learn Res 26:102–126
Daumé H, Kumar A, Saha A (2010) Co-regularization based semi-supervised domain adaptation. In: Advances in neural information processing systems (NIPS), Whistler
Evgeniou T, Micchelli CA, Pontil M (2005) Learning multiple tasks with kernel methods. J Mach Learn Res 6:615–637
Glorot X, Bordes A, Bengio Y (2011) Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the 28th international conference on machine learning (ICML), Bellevue, pp 513–520
Mansour Y, Mohri M, Rostamizadeh A (2009) Domain adaptation with multiple sources. In: Advances in neural information processing systems (NIPS), Whistler, pp 1041–1048
Mihalkova L, Huynh T, Mooney RJ (2007) Mapping and revising markov logic networks for transfer learning. In: Proceedings of the 22nd AAAI conference on artificial intelligence, Vancouver, pp 608–614
Oblinger D, Reid M, Brodie M, de Salvo Braz R (2002) Cross-training and its application to skill-mining. IBM Syst J 41(3):449–460
Pratt L, Thrun S (1997) Second special issue on inductive transfer. Mach Learn 28:4175
Quinonero-Candela J, Sugiyama M, Schwaighofer A, Lawrence ND (2009) Dataset shift in machine learning. MIT Press, Cambridge
Raina R, Ng AY, Koller D (2006) Constructing informative priors using transfer learning. In: Proceedings of the 23rd international conference on machine learning (ICML), Pittsburgh, pp 713–720
Reid M (2004) Improving rule evaluation using multitask learning. In: Proceedings of the 14th international conference on ILP, Porto, pp 252–269
Schmidhuber J (1997) Shifting inductive bias with success-story algorithm, adaptive levin search, and incremental self-improvement. Mach Learn 28:105–130
Stahl I (1995) Predicate invention in inductive logic programming. In: De Raedt L (ed) Advances in inductive logic programming. IOS Press, Amsterdam/Washington, DC, pp 34–47
Storkey A (2009) When training and test sets are different. In: Quinonero-Candela J, Sugiyama M, Schwaighofer A, Lawrence ND (eds) Dataset shift in machine learning. MIT Press, Cambridge, pp 3–28
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media New York
About this entry
Cite this entry
Vilalta, R., Giraud-Carrier, C., Brazdil, P., Soares, C. (2016). Inductive Transfer. In: Sammut, C., Webb, G. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7502-7_138-1
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7502-7_138-1
Received:
Accepted:
Published:
Publisher Name: Springer, Boston, MA
Online ISBN: 978-1-4899-7502-7
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering