An efficient learning method using a distributed support vector machine based on controlling data transger

Kiichiro Yukawa, Kenta Mikawa, Masayuki Goto

    Research output: Contribution to journalArticle

    Abstract

    The developments in information technology have highlighted the importance of analyzing big data stored in various databases. With this as a background, the importance of distributed data mining (DDM), which is the technique of implementing data mining while databases are not transmitting raw data to each other, has been advocated. As one of the methods, Forrero et al. proposed the method of optimal learning with a support vector machine (SVM) that uses the alternating direction method of multipliers (ADMM) in the context of DDM. The apparatus is called a consensus-based distributed support vector machine (D-SVM). This method can learn the optimal hyperplane with a relatively small number of iterations and minimal communication cost for an arbitrary network structure without sharing data. However, when the statistical characteristics of data stored in each database are quite different, this method requires many iterations until convergence. Needless to say, it is better that the number of iterations and total communication cost for the learning classifier are minimized. In this study, we propose a new and effective learning method that reduces the number of iterations considering the network structure, provided that all of the nodes are connected to each other. To verify the effectiveness of the proposed method, a simulation experiment using the UCI machine learning repository and artificial data is conducted.

    Original languageEnglish
    Pages (from-to)86-98
    Number of pages13
    JournalJournal of Japan Industrial Management Association
    Volume68
    Issue number2
    Publication statusPublished - 2017

    Fingerprint

    Support vector machines
    Data mining
    Support Vector Machine
    Distributed Data Mining
    Iteration
    Communication
    Communication Cost
    Network Structure
    Information technology
    Learning systems
    Costs
    Classifiers
    Method of multipliers
    Alternating Direction Method
    Data Sharing
    Information Technology
    Hyperplane
    Repository
    Simulation Experiment
    Learning

    Keywords

    • Distributed data mining
    • Graph structure
    • Support vector machine

    ASJC Scopus subject areas

    • Strategy and Management
    • Management Science and Operations Research
    • Industrial and Manufacturing Engineering
    • Applied Mathematics

    Cite this

    An efficient learning method using a distributed support vector machine based on controlling data transger. / Yukawa, Kiichiro; Mikawa, Kenta; Goto, Masayuki.

    In: Journal of Japan Industrial Management Association, Vol. 68, No. 2, 2017, p. 86-98.

    Research output: Contribution to journalArticle

    @article{a93292739f4e4119adc3e43494897847,
    title = "An efficient learning method using a distributed support vector machine based on controlling data transger",
    abstract = "The developments in information technology have highlighted the importance of analyzing big data stored in various databases. With this as a background, the importance of distributed data mining (DDM), which is the technique of implementing data mining while databases are not transmitting raw data to each other, has been advocated. As one of the methods, Forrero et al. proposed the method of optimal learning with a support vector machine (SVM) that uses the alternating direction method of multipliers (ADMM) in the context of DDM. The apparatus is called a consensus-based distributed support vector machine (D-SVM). This method can learn the optimal hyperplane with a relatively small number of iterations and minimal communication cost for an arbitrary network structure without sharing data. However, when the statistical characteristics of data stored in each database are quite different, this method requires many iterations until convergence. Needless to say, it is better that the number of iterations and total communication cost for the learning classifier are minimized. In this study, we propose a new and effective learning method that reduces the number of iterations considering the network structure, provided that all of the nodes are connected to each other. To verify the effectiveness of the proposed method, a simulation experiment using the UCI machine learning repository and artificial data is conducted.",
    keywords = "Distributed data mining, Graph structure, Support vector machine",
    author = "Kiichiro Yukawa and Kenta Mikawa and Masayuki Goto",
    year = "2017",
    language = "English",
    volume = "68",
    pages = "86--98",
    journal = "Journal of Japan Industrial Management Association",
    issn = "0386-4812",
    publisher = "Nihon Keikei Kogakkai",
    number = "2",

    }

    TY - JOUR

    T1 - An efficient learning method using a distributed support vector machine based on controlling data transger

    AU - Yukawa, Kiichiro

    AU - Mikawa, Kenta

    AU - Goto, Masayuki

    PY - 2017

    Y1 - 2017

    N2 - The developments in information technology have highlighted the importance of analyzing big data stored in various databases. With this as a background, the importance of distributed data mining (DDM), which is the technique of implementing data mining while databases are not transmitting raw data to each other, has been advocated. As one of the methods, Forrero et al. proposed the method of optimal learning with a support vector machine (SVM) that uses the alternating direction method of multipliers (ADMM) in the context of DDM. The apparatus is called a consensus-based distributed support vector machine (D-SVM). This method can learn the optimal hyperplane with a relatively small number of iterations and minimal communication cost for an arbitrary network structure without sharing data. However, when the statistical characteristics of data stored in each database are quite different, this method requires many iterations until convergence. Needless to say, it is better that the number of iterations and total communication cost for the learning classifier are minimized. In this study, we propose a new and effective learning method that reduces the number of iterations considering the network structure, provided that all of the nodes are connected to each other. To verify the effectiveness of the proposed method, a simulation experiment using the UCI machine learning repository and artificial data is conducted.

    AB - The developments in information technology have highlighted the importance of analyzing big data stored in various databases. With this as a background, the importance of distributed data mining (DDM), which is the technique of implementing data mining while databases are not transmitting raw data to each other, has been advocated. As one of the methods, Forrero et al. proposed the method of optimal learning with a support vector machine (SVM) that uses the alternating direction method of multipliers (ADMM) in the context of DDM. The apparatus is called a consensus-based distributed support vector machine (D-SVM). This method can learn the optimal hyperplane with a relatively small number of iterations and minimal communication cost for an arbitrary network structure without sharing data. However, when the statistical characteristics of data stored in each database are quite different, this method requires many iterations until convergence. Needless to say, it is better that the number of iterations and total communication cost for the learning classifier are minimized. In this study, we propose a new and effective learning method that reduces the number of iterations considering the network structure, provided that all of the nodes are connected to each other. To verify the effectiveness of the proposed method, a simulation experiment using the UCI machine learning repository and artificial data is conducted.

    KW - Distributed data mining

    KW - Graph structure

    KW - Support vector machine

    UR - http://www.scopus.com/inward/record.url?scp=85027447029&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85027447029&partnerID=8YFLogxK

    M3 - Article

    VL - 68

    SP - 86

    EP - 98

    JO - Journal of Japan Industrial Management Association

    JF - Journal of Japan Industrial Management Association

    SN - 0386-4812

    IS - 2

    ER -