Transfer Learning with Cluster Ensembles

Ayan Acharya, Eduardo R. Hruschka, Joydeep Ghosh, Sreangsu Acharyya
Proceedings of ICML Workshop on Unsupervised and Transfer Learning, PMLR 27:123-132, 2012.

Abstract

Traditional supervised learning algorithms typically assume that the training data and test data come from a common underlying distribution. Therefore, they are challenged by the mismatch between training and test distributions encountered in transfer learning situations. The problem is further exacerbated when the test data actually comes from a different domain and contains no labeled example. This paper describes an optimization framework that takes as input one or more classifiers learned on the source domain as well as the results of a cluster ensemble operating solely on the target domain, and yields a consensus labeling of the data in the target domain. This framework is fairly general in that it admits a wide range of loss functions and classification/clustering methods. Empirical results on both text and hyperspectral data indicate that the proposed method can yield superior classification results compared to applying certain other transductive and transfer learning techniques or naı̈vely applying the classifier (ensemble) learnt on the source domain to the target domain.

Cite this Paper

BibTeX
@InProceedings{pmlr-v27-acharya12a, title = {Transfer Learning with Cluster Ensembles}, author = {Acharya, Ayan and Hruschka, Eduardo R. and Ghosh, Joydeep and Acharyya, Sreangsu}, booktitle = {Proceedings of ICML Workshop on Unsupervised and Transfer Learning}, pages = {123--132}, year = {2012}, editor = {Guyon, Isabelle and Dror, Gideon and Lemaire, Vincent and Taylor, Graham and Silver, Daniel}, volume = {27}, series = {Proceedings of Machine Learning Research}, address = {Bellevue, Washington, USA}, month = {02 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v27/acharya12a/acharya12a.pdf}, url = {https://proceedings.mlr.press/v27/acharya12a.html}, abstract = {Traditional supervised learning algorithms typically assume that the training data and test data come from a common underlying distribution. Therefore, they are challenged by the mismatch between training and test distributions encountered in transfer learning situations. The problem is further exacerbated when the test data actually comes from a different domain and contains no labeled example. This paper describes an optimization framework that takes as input one or more classifiers learned on the source domain as well as the results of a cluster ensemble operating solely on the target domain, and yields a consensus labeling of the data in the target domain. This framework is fairly general in that it admits a wide range of loss functions and classification/clustering methods. Empirical results on both text and hyperspectral data indicate that the proposed method can yield superior classification results compared to applying certain other transductive and transfer learning techniques or naı̈vely applying the classifier (ensemble) learnt on the source domain to the target domain.} }
Endnote
%0 Conference Paper %T Transfer Learning with Cluster Ensembles %A Ayan Acharya %A Eduardo R. Hruschka %A Joydeep Ghosh %A Sreangsu Acharyya %B Proceedings of ICML Workshop on Unsupervised and Transfer Learning %C Proceedings of Machine Learning Research %D 2012 %E Isabelle Guyon %E Gideon Dror %E Vincent Lemaire %E Graham Taylor %E Daniel Silver %F pmlr-v27-acharya12a %I PMLR %P 123--132 %U https://proceedings.mlr.press/v27/acharya12a.html %V 27 %X Traditional supervised learning algorithms typically assume that the training data and test data come from a common underlying distribution. Therefore, they are challenged by the mismatch between training and test distributions encountered in transfer learning situations. The problem is further exacerbated when the test data actually comes from a different domain and contains no labeled example. This paper describes an optimization framework that takes as input one or more classifiers learned on the source domain as well as the results of a cluster ensemble operating solely on the target domain, and yields a consensus labeling of the data in the target domain. This framework is fairly general in that it admits a wide range of loss functions and classification/clustering methods. Empirical results on both text and hyperspectral data indicate that the proposed method can yield superior classification results compared to applying certain other transductive and transfer learning techniques or naı̈vely applying the classifier (ensemble) learnt on the source domain to the target domain.
RIS
TY - CPAPER TI - Transfer Learning with Cluster Ensembles AU - Ayan Acharya AU - Eduardo R. Hruschka AU - Joydeep Ghosh AU - Sreangsu Acharyya BT - Proceedings of ICML Workshop on Unsupervised and Transfer Learning DA - 2012/06/27 ED - Isabelle Guyon ED - Gideon Dror ED - Vincent Lemaire ED - Graham Taylor ED - Daniel Silver ID - pmlr-v27-acharya12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 27 SP - 123 EP - 132 L1 - http://proceedings.mlr.press/v27/acharya12a/acharya12a.pdf UR - https://proceedings.mlr.press/v27/acharya12a.html AB - Traditional supervised learning algorithms typically assume that the training data and test data come from a common underlying distribution. Therefore, they are challenged by the mismatch between training and test distributions encountered in transfer learning situations. The problem is further exacerbated when the test data actually comes from a different domain and contains no labeled example. This paper describes an optimization framework that takes as input one or more classifiers learned on the source domain as well as the results of a cluster ensemble operating solely on the target domain, and yields a consensus labeling of the data in the target domain. This framework is fairly general in that it admits a wide range of loss functions and classification/clustering methods. Empirical results on both text and hyperspectral data indicate that the proposed method can yield superior classification results compared to applying certain other transductive and transfer learning techniques or naı̈vely applying the classifier (ensemble) learnt on the source domain to the target domain. ER -
APA
Acharya, A., Hruschka, E.R., Ghosh, J. & Acharyya, S.. (2012). Transfer Learning with Cluster Ensembles. Proceedings of ICML Workshop on Unsupervised and Transfer Learning, in Proceedings of Machine Learning Research 27:123-132 Available from https://proceedings.mlr.press/v27/acharya12a.html.

Related Material