Abstract

As the relevant data sets get large, existing in-memory schemes for tensor decomposition become increasingly ineffective and, instead, memory-independent solutions, such as in-database analytics, are necessitated. In this paper, we present techniques for efficient implementations of in-database tensor decompositions on chunk-based array data stores. The proposed static and incremental in-database tensor decomposition operators and their optimizations address the constraints imposed by the main memory limitations when handling large and high-order tensor data. Firstly, we discuss how to implement alternating least squares operations efficiently on a chunk-based data storage system. Secondly, we consider scenarios with frequent data updates and show that compressed matrix multiplication techniques can be effective in reducing the incremental tensor decomposition maintenance costs. To the best of our knowledge, this paper presents the first attempt to develop efficient and optimized in-database tensor decomposition operations. We evaluate the proposed algorithms on tensor data sets that do not fit into the available memory and results show that the proposed techniques significantly improve the scalability of this core data analysis.

Original languageEnglish (US)
Title of host publicationCIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery, Inc
Pages969-978
Number of pages10
ISBN (Print)9781450325981
DOIs
StatePublished - Nov 3 2014
Event23rd ACM International Conference on Information and Knowledge Management, CIKM 2014 - Shanghai, China
Duration: Nov 3 2014Nov 7 2014

Other

Other23rd ACM International Conference on Information and Knowledge Management, CIKM 2014
CountryChina
CityShanghai
Period11/3/1411/7/14

Fingerprint

Tensors
Decomposition
Data storage equipment
Data base
Mathematical operators
Scalability
Costs
Incremental

Keywords

  • In-database tensor decomposition
  • Tensor decomposition

ASJC Scopus subject areas

  • Information Systems and Management
  • Computer Science Applications
  • Information Systems

Cite this

Kim, M., & Candan, K. (2014). Efficient static and dynamic in-database tensor decompositions on chunk-based array stores. In CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management (pp. 969-978). Association for Computing Machinery, Inc. https://doi.org/10.1145/2661829.2661864

Efficient static and dynamic in-database tensor decompositions on chunk-based array stores. / Kim, Mijung; Candan, Kasim.

CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, Inc, 2014. p. 969-978.

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

Kim, M & Candan, K 2014, Efficient static and dynamic in-database tensor decompositions on chunk-based array stores. in CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, Inc, pp. 969-978, 23rd ACM International Conference on Information and Knowledge Management, CIKM 2014, Shanghai, China, 11/3/14. https://doi.org/10.1145/2661829.2661864
Kim M, Candan K. Efficient static and dynamic in-database tensor decompositions on chunk-based array stores. In CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, Inc. 2014. p. 969-978 https://doi.org/10.1145/2661829.2661864
Kim, Mijung ; Candan, Kasim. / Efficient static and dynamic in-database tensor decompositions on chunk-based array stores. CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, Inc, 2014. pp. 969-978
@inproceedings{d159566eda95414693828a53808a3bf4,
title = "Efficient static and dynamic in-database tensor decompositions on chunk-based array stores",
abstract = "As the relevant data sets get large, existing in-memory schemes for tensor decomposition become increasingly ineffective and, instead, memory-independent solutions, such as in-database analytics, are necessitated. In this paper, we present techniques for efficient implementations of in-database tensor decompositions on chunk-based array data stores. The proposed static and incremental in-database tensor decomposition operators and their optimizations address the constraints imposed by the main memory limitations when handling large and high-order tensor data. Firstly, we discuss how to implement alternating least squares operations efficiently on a chunk-based data storage system. Secondly, we consider scenarios with frequent data updates and show that compressed matrix multiplication techniques can be effective in reducing the incremental tensor decomposition maintenance costs. To the best of our knowledge, this paper presents the first attempt to develop efficient and optimized in-database tensor decomposition operations. We evaluate the proposed algorithms on tensor data sets that do not fit into the available memory and results show that the proposed techniques significantly improve the scalability of this core data analysis.",
keywords = "In-database tensor decomposition, Tensor decomposition",
author = "Mijung Kim and Kasim Candan",
year = "2014",
month = "11",
day = "3",
doi = "10.1145/2661829.2661864",
language = "English (US)",
isbn = "9781450325981",
pages = "969--978",
booktitle = "CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Efficient static and dynamic in-database tensor decompositions on chunk-based array stores

AU - Kim, Mijung

AU - Candan, Kasim

PY - 2014/11/3

Y1 - 2014/11/3

N2 - As the relevant data sets get large, existing in-memory schemes for tensor decomposition become increasingly ineffective and, instead, memory-independent solutions, such as in-database analytics, are necessitated. In this paper, we present techniques for efficient implementations of in-database tensor decompositions on chunk-based array data stores. The proposed static and incremental in-database tensor decomposition operators and their optimizations address the constraints imposed by the main memory limitations when handling large and high-order tensor data. Firstly, we discuss how to implement alternating least squares operations efficiently on a chunk-based data storage system. Secondly, we consider scenarios with frequent data updates and show that compressed matrix multiplication techniques can be effective in reducing the incremental tensor decomposition maintenance costs. To the best of our knowledge, this paper presents the first attempt to develop efficient and optimized in-database tensor decomposition operations. We evaluate the proposed algorithms on tensor data sets that do not fit into the available memory and results show that the proposed techniques significantly improve the scalability of this core data analysis.

AB - As the relevant data sets get large, existing in-memory schemes for tensor decomposition become increasingly ineffective and, instead, memory-independent solutions, such as in-database analytics, are necessitated. In this paper, we present techniques for efficient implementations of in-database tensor decompositions on chunk-based array data stores. The proposed static and incremental in-database tensor decomposition operators and their optimizations address the constraints imposed by the main memory limitations when handling large and high-order tensor data. Firstly, we discuss how to implement alternating least squares operations efficiently on a chunk-based data storage system. Secondly, we consider scenarios with frequent data updates and show that compressed matrix multiplication techniques can be effective in reducing the incremental tensor decomposition maintenance costs. To the best of our knowledge, this paper presents the first attempt to develop efficient and optimized in-database tensor decomposition operations. We evaluate the proposed algorithms on tensor data sets that do not fit into the available memory and results show that the proposed techniques significantly improve the scalability of this core data analysis.

KW - In-database tensor decomposition

KW - Tensor decomposition

UR - http://www.scopus.com/inward/record.url?scp=84937560308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937560308&partnerID=8YFLogxK

U2 - 10.1145/2661829.2661864

DO - 10.1145/2661829.2661864

M3 - Conference contribution

SN - 9781450325981

SP - 969

EP - 978

BT - CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery, Inc

ER -