Multi-view learning with dependent views

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Standard

Multi-view learning with dependent views. / Brefeld, Ulf.
2015 Symposium on Applied Computing, SAC 2015: Proceedings of the 30th Annual ACM Symposium on Applied Computing. ed. / Dongwan Shin. Association for Computing Machinery, Inc, 2015. p. 865-870 (Proceedings of the ACM Symposium on Applied Computing; Vol. 13-17-April-2015).

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Harvard

Brefeld, U 2015, Multi-view learning with dependent views. in D Shin (ed.), 2015 Symposium on Applied Computing, SAC 2015: Proceedings of the 30th Annual ACM Symposium on Applied Computing. Proceedings of the ACM Symposium on Applied Computing, vol. 13-17-April-2015, Association for Computing Machinery, Inc, pp. 865-870, 30th Annual ACM Symposium on Applied Computing - SAC 2015, Salamanca, Spain, 13.04.15. https://doi.org/10.1145/2695664.2695829

APA

Brefeld, U. (2015). Multi-view learning with dependent views. In D. Shin (Ed.), 2015 Symposium on Applied Computing, SAC 2015: Proceedings of the 30th Annual ACM Symposium on Applied Computing (pp. 865-870). (Proceedings of the ACM Symposium on Applied Computing; Vol. 13-17-April-2015). Association for Computing Machinery, Inc. https://doi.org/10.1145/2695664.2695829

Vancouver

Brefeld U. Multi-view learning with dependent views. In Shin D, editor, 2015 Symposium on Applied Computing, SAC 2015: Proceedings of the 30th Annual ACM Symposium on Applied Computing. Association for Computing Machinery, Inc. 2015. p. 865-870. (Proceedings of the ACM Symposium on Applied Computing). doi: 10.1145/2695664.2695829

Bibtex

@inbook{1b7adf602ce444589dbce9a31ad02dc6,
title = "Multi-view learning with dependent views",
abstract = "Multi-view algorithms, such as co-training and co-EM, utilize unlabeled data when the available attributes can be split into independent and compatible subsets. Experiments have shown that multi-view learning is sometimes beneficial for problems for which the independence assumption is not satis fied. In practice, unfortunately, it is not possible to measure the dependency between two attribute sets; hence, there is no criterion which allows to decide whether multi-view learning is applicable. We conduct experiments with various text classification problems and investigate on the effectiveness of the co-trained SVM and the co-EM SVM under various conditions, including violations of the independence assumption. We identify the error correlation coefficient of the initial classifiers as an elaborate indicator of the expected benefit of multi-view learning. Copyright is held by the owner/author(s).",
keywords = "Informatics, Business informatics, Multi-view learning",
author = "Ulf Brefeld",
year = "2015",
month = apr,
day = "13",
doi = "10.1145/2695664.2695829",
language = "English",
isbn = "978-1-4503-3196-8 ",
series = "Proceedings of the ACM Symposium on Applied Computing",
publisher = "Association for Computing Machinery, Inc",
pages = "865--870",
editor = "Dongwan Shin",
booktitle = "2015 Symposium on Applied Computing, SAC 2015",
address = "United States",
note = "30th Annual ACM Symposium on Applied Computing - SAC 2015, SAC 2015 ; Conference date: 13-04-2015 Through 17-04-2015",
url = "https://www.sigapp.org/sac/sac2015/",

}

RIS

TY - CHAP

T1 - Multi-view learning with dependent views

AU - Brefeld, Ulf

N1 - Conference code: 30

PY - 2015/4/13

Y1 - 2015/4/13

N2 - Multi-view algorithms, such as co-training and co-EM, utilize unlabeled data when the available attributes can be split into independent and compatible subsets. Experiments have shown that multi-view learning is sometimes beneficial for problems for which the independence assumption is not satis fied. In practice, unfortunately, it is not possible to measure the dependency between two attribute sets; hence, there is no criterion which allows to decide whether multi-view learning is applicable. We conduct experiments with various text classification problems and investigate on the effectiveness of the co-trained SVM and the co-EM SVM under various conditions, including violations of the independence assumption. We identify the error correlation coefficient of the initial classifiers as an elaborate indicator of the expected benefit of multi-view learning. Copyright is held by the owner/author(s).

AB - Multi-view algorithms, such as co-training and co-EM, utilize unlabeled data when the available attributes can be split into independent and compatible subsets. Experiments have shown that multi-view learning is sometimes beneficial for problems for which the independence assumption is not satis fied. In practice, unfortunately, it is not possible to measure the dependency between two attribute sets; hence, there is no criterion which allows to decide whether multi-view learning is applicable. We conduct experiments with various text classification problems and investigate on the effectiveness of the co-trained SVM and the co-EM SVM under various conditions, including violations of the independence assumption. We identify the error correlation coefficient of the initial classifiers as an elaborate indicator of the expected benefit of multi-view learning. Copyright is held by the owner/author(s).

KW - Informatics

KW - Business informatics

KW - Multi-view learning

UR - http://www.scopus.com/inward/record.url?scp=84955514727&partnerID=8YFLogxK

U2 - 10.1145/2695664.2695829

DO - 10.1145/2695664.2695829

M3 - Article in conference proceedings

SN - 978-1-4503-3196-8

T3 - Proceedings of the ACM Symposium on Applied Computing

SP - 865

EP - 870

BT - 2015 Symposium on Applied Computing, SAC 2015

A2 - Shin, Dongwan

PB - Association for Computing Machinery, Inc

T2 - 30th Annual ACM Symposium on Applied Computing - SAC 2015

Y2 - 13 April 2015 through 17 April 2015

ER -

DOI