Conformal feature-selection wrappers for instance transfer

Shuang Zhou; Evgueni Smirnov; Gijs Schoenmakers; Ralf Peeters; Tao Jiang

Conformal feature-selection wrappers for instance transfer

Shuang Zhou, Evgueni Smirnov, Gijs Schoenmakers, Ralf Peeters, Tao Jiang

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

19 Downloads (Pure)

Abstract

In this paper we propose a new method of conformal feature-selection wrappers for instance transfer (CFSWIT). Given target and source data, the method optimally selects features and source data that are relevant for a classification model. The CFSWIT method is model-independent. It was tested experimentally for several types of classifiers. The experiments show that the CFSWIT method is capable of outperforming standard instance transfer methods.

Original language	English
Title of host publication	Proceedings of the 7th Symposium on Conformal and Probabilistic Prediction and Applications, COPA 2018, 11-13 June 2018, Maastricht, The Netherlands.
Publisher	Proceedings of Machine Learning Research
Pages	96-113
Number of pages	18
Volume	91
Publication status	Published - 2018

Access to Document

Full text Final published version, 294 KBLicence: Taverne

Cite this

@inproceedings{bf8a376442f54544a8f1d3ec480973ce,

title = "Conformal feature-selection wrappers for instance transfer",

abstract = "In this paper we propose a new method of conformal feature-selection wrappers for instance transfer (CFSWIT). Given target and source data, the method optimally selects features and source data that are relevant for a classification model. The CFSWIT method is model-independent. It was tested experimentally for several types of classifiers. The experiments show that the CFSWIT method is capable of outperforming standard instance transfer methods.",

author = "Shuang Zhou and Evgueni Smirnov and Gijs Schoenmakers and Ralf Peeters and Tao Jiang",

year = "2018",

language = "English",

volume = "91",

pages = "96--113",

booktitle = "Proceedings of the 7th Symposium on Conformal and Probabilistic Prediction and Applications, COPA 2018, 11-13 June 2018, Maastricht, The Netherlands.",

publisher = "Proceedings of Machine Learning Research",

}

Conformal feature-selection wrappers for instance transfer. / Zhou, Shuang; Smirnov, Evgueni ; Schoenmakers, Gijs et al.
Proceedings of the 7th Symposium on Conformal and Probabilistic Prediction and Applications, COPA 2018, 11-13 June 2018, Maastricht, The Netherlands.. Vol. 91 Proceedings of Machine Learning Research, 2018. p. 96-113.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Conformal feature-selection wrappers for instance transfer

AU - Zhou, Shuang

AU - Smirnov, Evgueni

AU - Schoenmakers, Gijs

AU - Peeters, Ralf

AU - Jiang, Tao

PY - 2018

Y1 - 2018

N2 - In this paper we propose a new method of conformal feature-selection wrappers for instance transfer (CFSWIT). Given target and source data, the method optimally selects features and source data that are relevant for a classification model. The CFSWIT method is model-independent. It was tested experimentally for several types of classifiers. The experiments show that the CFSWIT method is capable of outperforming standard instance transfer methods.

AB - In this paper we propose a new method of conformal feature-selection wrappers for instance transfer (CFSWIT). Given target and source data, the method optimally selects features and source data that are relevant for a classification model. The CFSWIT method is model-independent. It was tested experimentally for several types of classifiers. The experiments show that the CFSWIT method is capable of outperforming standard instance transfer methods.

M3 - Conference article in proceeding

VL - 91

SP - 96

EP - 113

BT - Proceedings of the 7th Symposium on Conformal and Probabilistic Prediction and Applications, COPA 2018, 11-13 June 2018, Maastricht, The Netherlands.

PB - Proceedings of Machine Learning Research

ER -

Conformal feature-selection wrappers for instance transfer

Abstract

Access to Document

Fingerprint

Cite this