Modular Dimensionality Reduction

Henry W J Reeve; Tingting Mu; Gavin Brown

doi:10.1007/978-3-030-10925-7_37

Modular Dimensionality Reduction

Henry W J Reeve^*, Tingting Mu, Gavin Brown

^*Corresponding author for this work

School of Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

2 Citations (Scopus)

122 Downloads (Pure)

Abstract

We introduce an approach to modular dimensionality reduction, allowing efficient learning of multiple complementary representations of the same object. Modules are trained by optimising an unsupervised cost function which balances two competing goals: Maintaining the inner product structure within the original space, and encouraging structural diversity between complementary representations. We derive an efficient learning algorithm which outperforms gradient based approaches without the need to choose a learning rate. We also demonstrate anintriguing connection with Dropout. Empirical results demonstrate the efficacy of the method for image retrieval and classification.

Original language	English
Title of host publication	Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2018
Publisher	Springer
Pages	605-619
Number of pages	15
ISBN (Electronic)	978-3-030-10925-7
ISBN (Print)	978-3-030-10924-0
DOIs	https://doi.org/10.1007/978-3-030-10925-7_37
Publication status	Published - 18 Jan 2019
Event	European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - Dublin, Ireland Duration: 10 Sept 2018 → 14 Sept 2018 http://www.ecmlpkdd2018.org/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer, Cham
Volume	11051
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Abbreviated title	ECML PKDD 2018
Country/Territory	Ireland
City	Dublin
Period	10/09/18 → 14/09/18
Internet address	http://www.ecmlpkdd2018.org/

Keywords

Ensemble learning
Dimensionality reduction
Dropout
Kernel principal components analysis

Access to Document

10.1007/978-3-030-10925-7_37

Full-text PDF (author accepted manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via Springer Nature at https://link.springer.com/chapter/10.1007%2F978-3-030-10925-7_37. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 696 KB

Handle.net

Persistent link

Cite this

@inproceedings{04566ac55d8a45058d03160f4ae86a1f,

title = "Modular Dimensionality Reduction",

abstract = "We introduce an approach to modular dimensionality reduction, allowing efficient learning of multiple complementary representations of the same object. Modules are trained by optimising an unsupervised cost function which balances two competing goals: Maintaining the inner product structure within the original space, and encouraging structural diversity between complementary representations. We derive an efficient learning algorithm which outperforms gradient based approaches without the need to choose a learning rate. We also demonstrate anintriguing connection with Dropout. Empirical results demonstrate the efficacy of the method for image retrieval and classification.",

keywords = "Ensemble learning, Dimensionality reduction, Dropout, Kernel principal components analysis",

author = "Reeve, \{Henry W J\} and Tingting Mu and Gavin Brown",

year = "2019",

month = jan,

day = "18",

doi = "10.1007/978-3-030-10925-7\_37",

language = "English",

isbn = "978-3-030-10924-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "605--619",

booktitle = "Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2018",

address = "United States",

note = "European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases , ECML PKDD 2018 ; Conference date: 10-09-2018 Through 14-09-2018",

url = "http://www.ecmlpkdd2018.org/",

}

Reeve, HWJ, Mu, T & Brown, G 2019, Modular Dimensionality Reduction. in Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2018. Lecture Notes in Computer Science, vol. 11051, Springer, pp. 605-619, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases , Dublin, Ireland, 10/09/18. https://doi.org/10.1007/978-3-030-10925-7_37

Modular Dimensionality Reduction. / Reeve, Henry W J; Mu, Tingting; Brown, Gavin.
Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2018. Springer, 2019. p. 605-619 (Lecture Notes in Computer Science; Vol. 11051).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Modular Dimensionality Reduction

AU - Reeve, Henry W J

AU - Mu, Tingting

AU - Brown, Gavin

PY - 2019/1/18

Y1 - 2019/1/18

N2 - We introduce an approach to modular dimensionality reduction, allowing efficient learning of multiple complementary representations of the same object. Modules are trained by optimising an unsupervised cost function which balances two competing goals: Maintaining the inner product structure within the original space, and encouraging structural diversity between complementary representations. We derive an efficient learning algorithm which outperforms gradient based approaches without the need to choose a learning rate. We also demonstrate anintriguing connection with Dropout. Empirical results demonstrate the efficacy of the method for image retrieval and classification.

AB - We introduce an approach to modular dimensionality reduction, allowing efficient learning of multiple complementary representations of the same object. Modules are trained by optimising an unsupervised cost function which balances two competing goals: Maintaining the inner product structure within the original space, and encouraging structural diversity between complementary representations. We derive an efficient learning algorithm which outperforms gradient based approaches without the need to choose a learning rate. We also demonstrate anintriguing connection with Dropout. Empirical results demonstrate the efficacy of the method for image retrieval and classification.

KW - Ensemble learning

KW - Dimensionality reduction

KW - Dropout

KW - Kernel principal components analysis

U2 - 10.1007/978-3-030-10925-7_37

DO - 10.1007/978-3-030-10925-7_37

M3 - Conference Contribution (Conference Proceeding)

SN - 978-3-030-10924-0

T3 - Lecture Notes in Computer Science

SP - 605

EP - 619

BT - Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2018

PB - Springer

T2 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases

Y2 - 10 September 2018 through 14 September 2018

ER -

Modular Dimensionality Reduction

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this