Ensembles based on conformal instance transfer

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

In this paper we propose a new ensemble method based on conformal instance transfer. The method combines feature selection and source-instance selection to avoid negative transfer in a model-independent way. It was tested experimentally for dierent types of classiers on several benchmark data sets. The experiment results demonstrate that the new method is capable of outperforming signicantly standard instance transfer methods. Keywords: Instance Transfer, Conformal Prediction, Ensembles
Original languageEnglish
Title of host publicationProceedings of Machine Learning Research
Subtitle of host publicationConformal and Probabilistic Prediction and Applications, 9-11 September 2019, Golden Sands, Bulgaria
Pages23-42
Volume105
Publication statusPublished - 2019

Publication series

SeriesProceedings of Machine Learning Research
ISSN2640-3498

Cite this

Zhou, S., Smirnov, E., & Schoenmakers, G. (2019). Ensembles based on conformal instance transfer. In Proceedings of Machine Learning Research: Conformal and Probabilistic Prediction and Applications, 9-11 September 2019, Golden Sands, Bulgaria (Vol. 105, pp. 23-42). Proceedings of Machine Learning Research http://proceedings.mlr.press/v105/zhou19a/zhou19a.pdf