Norm emergence via influential weight propagation in complex networks

Ryosuke Shibusawa, Toshiharu Sugawara

    研究成果: Conference contribution

    9 引用 (Scopus)

    抄録

    We propose an influence-based aggregative learning framework that facilitates the emergence of social norms in complex networks and investigate how a norm converges by learning through iterated local interactions in a coordination game. In society, humans decide to coordinate their behavior not only by exchanging information but also on the basis of norms that are often individually derived from interactions without a centralized authority. Coordination using norms has received much attention in studies of multi-agent systems. In addition, because agents often work as delegates of humans, they should have 'mental' models about how to interact with others and incorporate differences of opinion. Because norms make sense only when all or most agents have the same one and they can expect that others will follow, it is important to investigate the mechanism of norm emergence through learning with local and individual interactions in agent society. Our method of norm learning borrows from the opinion aggregation process while taking into account the influence of local opinions in tightly coordinated human communities. We conducted experiments showing how our learning framework facilitates propagation of norms in a number of complex agent networks.

    元の言語English
    ホスト出版物のタイトルProceedings - 2014 European Network Intelligence Conference, ENIC 2014
    出版者Institute of Electrical and Electronics Engineers Inc.
    ページ30-37
    ページ数8
    ISBN(印刷物)9781479969142
    DOI
    出版物ステータスPublished - 2014 12 12
    イベント1st European Network Intelligence Conference, ENIC 2014 - Wroclaw
    継続期間: 2014 9 292014 9 30

    Other

    Other1st European Network Intelligence Conference, ENIC 2014
    Wroclaw
    期間14/9/2914/9/30

    Fingerprint

    Complex networks
    Multi agent systems
    Agglomeration
    Experiments

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Computer Networks and Communications
    • Electrical and Electronic Engineering
    • Information Systems

    これを引用

    Shibusawa, R., & Sugawara, T. (2014). Norm emergence via influential weight propagation in complex networks. : Proceedings - 2014 European Network Intelligence Conference, ENIC 2014 (pp. 30-37). [6984887] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ENIC.2014.28

    Norm emergence via influential weight propagation in complex networks. / Shibusawa, Ryosuke; Sugawara, Toshiharu.

    Proceedings - 2014 European Network Intelligence Conference, ENIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 30-37 6984887.

    研究成果: Conference contribution

    Shibusawa, R & Sugawara, T 2014, Norm emergence via influential weight propagation in complex networks. : Proceedings - 2014 European Network Intelligence Conference, ENIC 2014., 6984887, Institute of Electrical and Electronics Engineers Inc., pp. 30-37, 1st European Network Intelligence Conference, ENIC 2014, Wroclaw, 14/9/29. https://doi.org/10.1109/ENIC.2014.28
    Shibusawa R, Sugawara T. Norm emergence via influential weight propagation in complex networks. : Proceedings - 2014 European Network Intelligence Conference, ENIC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 30-37. 6984887 https://doi.org/10.1109/ENIC.2014.28
    Shibusawa, Ryosuke ; Sugawara, Toshiharu. / Norm emergence via influential weight propagation in complex networks. Proceedings - 2014 European Network Intelligence Conference, ENIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 30-37
    @inproceedings{2c96234ece0346ffb59c0c053ff301c9,
    title = "Norm emergence via influential weight propagation in complex networks",
    abstract = "We propose an influence-based aggregative learning framework that facilitates the emergence of social norms in complex networks and investigate how a norm converges by learning through iterated local interactions in a coordination game. In society, humans decide to coordinate their behavior not only by exchanging information but also on the basis of norms that are often individually derived from interactions without a centralized authority. Coordination using norms has received much attention in studies of multi-agent systems. In addition, because agents often work as delegates of humans, they should have 'mental' models about how to interact with others and incorporate differences of opinion. Because norms make sense only when all or most agents have the same one and they can expect that others will follow, it is important to investigate the mechanism of norm emergence through learning with local and individual interactions in agent society. Our method of norm learning borrows from the opinion aggregation process while taking into account the influence of local opinions in tightly coordinated human communities. We conducted experiments showing how our learning framework facilitates propagation of norms in a number of complex agent networks.",
    keywords = "Complex Network, Influence, Multi Agent System, Norm, Reinforcement learning",
    author = "Ryosuke Shibusawa and Toshiharu Sugawara",
    year = "2014",
    month = "12",
    day = "12",
    doi = "10.1109/ENIC.2014.28",
    language = "English",
    isbn = "9781479969142",
    pages = "30--37",
    booktitle = "Proceedings - 2014 European Network Intelligence Conference, ENIC 2014",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Norm emergence via influential weight propagation in complex networks

    AU - Shibusawa, Ryosuke

    AU - Sugawara, Toshiharu

    PY - 2014/12/12

    Y1 - 2014/12/12

    N2 - We propose an influence-based aggregative learning framework that facilitates the emergence of social norms in complex networks and investigate how a norm converges by learning through iterated local interactions in a coordination game. In society, humans decide to coordinate their behavior not only by exchanging information but also on the basis of norms that are often individually derived from interactions without a centralized authority. Coordination using norms has received much attention in studies of multi-agent systems. In addition, because agents often work as delegates of humans, they should have 'mental' models about how to interact with others and incorporate differences of opinion. Because norms make sense only when all or most agents have the same one and they can expect that others will follow, it is important to investigate the mechanism of norm emergence through learning with local and individual interactions in agent society. Our method of norm learning borrows from the opinion aggregation process while taking into account the influence of local opinions in tightly coordinated human communities. We conducted experiments showing how our learning framework facilitates propagation of norms in a number of complex agent networks.

    AB - We propose an influence-based aggregative learning framework that facilitates the emergence of social norms in complex networks and investigate how a norm converges by learning through iterated local interactions in a coordination game. In society, humans decide to coordinate their behavior not only by exchanging information but also on the basis of norms that are often individually derived from interactions without a centralized authority. Coordination using norms has received much attention in studies of multi-agent systems. In addition, because agents often work as delegates of humans, they should have 'mental' models about how to interact with others and incorporate differences of opinion. Because norms make sense only when all or most agents have the same one and they can expect that others will follow, it is important to investigate the mechanism of norm emergence through learning with local and individual interactions in agent society. Our method of norm learning borrows from the opinion aggregation process while taking into account the influence of local opinions in tightly coordinated human communities. We conducted experiments showing how our learning framework facilitates propagation of norms in a number of complex agent networks.

    KW - Complex Network

    KW - Influence

    KW - Multi Agent System

    KW - Norm

    KW - Reinforcement learning

    UR - http://www.scopus.com/inward/record.url?scp=84921019900&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84921019900&partnerID=8YFLogxK

    U2 - 10.1109/ENIC.2014.28

    DO - 10.1109/ENIC.2014.28

    M3 - Conference contribution

    AN - SCOPUS:84921019900

    SN - 9781479969142

    SP - 30

    EP - 37

    BT - Proceedings - 2014 European Network Intelligence Conference, ENIC 2014

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -