Bayesian supervised multilabel learning with coupled embedding and classification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Coupled training of dimensionality reduction and classifica- Tion is proposed previously to improve the prediction per- formance for single-label problems. Following this line of research, in this paper, we introduce a novel Bayesian su- pervised multilabel learning method that combines linear di- mensionality reduction with linear binary classification. We present a deterministic variational approximation approach to learn the proposed probabilistic model for multilabel clas- sification. We perform experiments on four benchmark mul- Tilabel learning data sets by comparing our method with four baseline linear dimensionality reduction algorithms. Exper- iments show that the proposed approach achieves good per- formance values in terms of hamming loss, macro F1, and micro F1 on held-out test data. The low-dimensional em- beddings obtained by our method are also very useful for exploratory data analysis.

Original languageEnglish (US)
Title of host publicationProceedings of the 12th SIAM International Conference on Data Mining, SDM 2012
Pages367-378
Number of pages12
StatePublished - 2012
Externally publishedYes
Event12th SIAM International Conference on Data Mining, SDM 2012 - Anaheim, CA, United States
Duration: Apr 26 2012Apr 28 2012

Other

Other12th SIAM International Conference on Data Mining, SDM 2012
CountryUnited States
CityAnaheim, CA
Period4/26/124/28/12

Fingerprint

Supervised learning
Macros
Labels
Experiments

ASJC Scopus subject areas

  • Computer Science Applications

Cite this

Gonen, M. (2012). Bayesian supervised multilabel learning with coupled embedding and classification. In Proceedings of the 12th SIAM International Conference on Data Mining, SDM 2012 (pp. 367-378)

Bayesian supervised multilabel learning with coupled embedding and classification. / Gonen, Mehmet.

Proceedings of the 12th SIAM International Conference on Data Mining, SDM 2012. 2012. p. 367-378.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gonen, M 2012, Bayesian supervised multilabel learning with coupled embedding and classification. in Proceedings of the 12th SIAM International Conference on Data Mining, SDM 2012. pp. 367-378, 12th SIAM International Conference on Data Mining, SDM 2012, Anaheim, CA, United States, 4/26/12.
Gonen M. Bayesian supervised multilabel learning with coupled embedding and classification. In Proceedings of the 12th SIAM International Conference on Data Mining, SDM 2012. 2012. p. 367-378
Gonen, Mehmet. / Bayesian supervised multilabel learning with coupled embedding and classification. Proceedings of the 12th SIAM International Conference on Data Mining, SDM 2012. 2012. pp. 367-378
@inproceedings{7e5d9a785d894c1f912380a3bcd86b3e,
title = "Bayesian supervised multilabel learning with coupled embedding and classification",
abstract = "Coupled training of dimensionality reduction and classifica- Tion is proposed previously to improve the prediction per- formance for single-label problems. Following this line of research, in this paper, we introduce a novel Bayesian su- pervised multilabel learning method that combines linear di- mensionality reduction with linear binary classification. We present a deterministic variational approximation approach to learn the proposed probabilistic model for multilabel clas- sification. We perform experiments on four benchmark mul- Tilabel learning data sets by comparing our method with four baseline linear dimensionality reduction algorithms. Exper- iments show that the proposed approach achieves good per- formance values in terms of hamming loss, macro F1, and micro F1 on held-out test data. The low-dimensional em- beddings obtained by our method are also very useful for exploratory data analysis.",
author = "Mehmet Gonen",
year = "2012",
language = "English (US)",
isbn = "9781611972320",
pages = "367--378",
booktitle = "Proceedings of the 12th SIAM International Conference on Data Mining, SDM 2012",

}

TY - GEN

T1 - Bayesian supervised multilabel learning with coupled embedding and classification

AU - Gonen, Mehmet

PY - 2012

Y1 - 2012

N2 - Coupled training of dimensionality reduction and classifica- Tion is proposed previously to improve the prediction per- formance for single-label problems. Following this line of research, in this paper, we introduce a novel Bayesian su- pervised multilabel learning method that combines linear di- mensionality reduction with linear binary classification. We present a deterministic variational approximation approach to learn the proposed probabilistic model for multilabel clas- sification. We perform experiments on four benchmark mul- Tilabel learning data sets by comparing our method with four baseline linear dimensionality reduction algorithms. Exper- iments show that the proposed approach achieves good per- formance values in terms of hamming loss, macro F1, and micro F1 on held-out test data. The low-dimensional em- beddings obtained by our method are also very useful for exploratory data analysis.

AB - Coupled training of dimensionality reduction and classifica- Tion is proposed previously to improve the prediction per- formance for single-label problems. Following this line of research, in this paper, we introduce a novel Bayesian su- pervised multilabel learning method that combines linear di- mensionality reduction with linear binary classification. We present a deterministic variational approximation approach to learn the proposed probabilistic model for multilabel clas- sification. We perform experiments on four benchmark mul- Tilabel learning data sets by comparing our method with four baseline linear dimensionality reduction algorithms. Exper- iments show that the proposed approach achieves good per- formance values in terms of hamming loss, macro F1, and micro F1 on held-out test data. The low-dimensional em- beddings obtained by our method are also very useful for exploratory data analysis.

UR - http://www.scopus.com/inward/record.url?scp=84880216558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880216558&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84880216558

SN - 9781611972320

SP - 367

EP - 378

BT - Proceedings of the 12th SIAM International Conference on Data Mining, SDM 2012

ER -