WEKO3
アイテム
{"_buckets": {"deposit": "74dafe25-9320-485f-88b1-9f3df58daf49"}, "_deposit": {"id": "54778", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "54778"}, "status": "published"}, "_oai": {"id": "oai:tsukuba.repo.nii.ac.jp:00054778", "sets": ["6669", "4944", "7974"]}, "item_5_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2020-06", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "2", "bibliographicPageStart": "04020018", "bibliographicVolumeNumber": "6", "bibliographic_titles": [{}, {"bibliographic_title": "ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering", "bibliographic_titleLang": "en"}]}]}, "item_5_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "This paper proposes a data collaboration analysis framework for distributed data sets. The proposed framework involves centralized machine learning while the original data sets and models remain distributed over a number of institutions. Recently, data has become larger and more distributed with decreasing costs of data collection. Centralizing distributed data sets and analyzing them as one data set can allow for novel insights and attainment of higher prediction performance than that of analyzing distributed data sets individually. However, it is generally difficult to centralize the original data sets because of a large data size or privacy concerns. This paper proposes a data collaboration analysis framework that does not involve sharing the original data sets to circumvent these difficulties. The proposed framework only centralizes intermediate representations constructed individually rather than the original data set. The proposed framework does not use privacy-preserving computations or model centralization. In addition, this paper proposes a practical algorithm within the framework. Numerical experiments reveal that the proposed method achieves higher recognition performance for artificial and real-world problems than individual analysis.", "subitem_description_type": "Abstract"}]}, "item_5_publisher_27": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "American Society of Civil Engineers"}]}, "item_5_relation_11": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1061/AJRUA6.0001058", "subitem_relation_type_select": "DOI"}}]}, "item_5_rights_12": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "© ASCE"}, {"subitem_rights": "This work is made available under the terms of the Creative Commons Attribution 4.0 International license, http://creativecommons.org/licenses/by/4.0/."}]}, "item_5_select_15": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_5_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "2376-7642", "subitem_source_identifier_type": "ISSN"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "今倉, 暁"}, {"creatorName": "イマクラ, アキラ", "creatorNameLang": "ja-Kana"}, {"creatorName": "IMAKURA, Akira", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "201384", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "60610045", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000060610045"}, {"nameIdentifier": "0000003376", "nameIdentifierScheme": "筑波大学研究者総覧", "nameIdentifierURI": "http://trios.tsukuba.ac.jp/researcher/0000003376"}]}, {"creatorNames": [{"creatorName": "櫻井, 鉄也"}, {"creatorName": "サクライ, テツヤ", "creatorNameLang": "ja-Kana"}, {"creatorName": "SAKURAI, Tetsuya", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "127985", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "60187086", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000060187086"}, {"nameIdentifier": "0000000941", "nameIdentifierScheme": "筑波大学研究者総覧", "nameIdentifierURI": "http://trios.tsukuba.ac.jp/researcher/0000000941"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2020-06-23"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "ASCE-ASME-B_6-2.pdf", "filesize": [{"value": "1.4 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_6", "mimetype": "application/pdf", "size": 1400000.0, "url": {"label": "ASCE-ASME-B_6-2", "url": "https://tsukuba.repo.nii.ac.jp/record/54778/files/ASCE-ASME-B_6-2.pdf"}, "version_id": "1c74f552-657a-48db-a2eb-0795e90b71ba"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Data Collaboration Analysis Framework Using Centralization of Individual Intermediate Representations for Distributed Data Sets", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Data Collaboration Analysis Framework Using Centralization of Individual Intermediate Representations for Distributed Data Sets", "subitem_title_language": "en"}]}, "item_type_id": "5", "owner": "1", "path": ["6669", "4944", "7974"], "permalink_uri": "http://hdl.handle.net/2241/00160187", "pubdate": {"attribute_name": "公開日", "attribute_value": "2020-06-23"}, "publish_date": "2020-06-23", "publish_status": "0", "recid": "54778", "relation": {}, "relation_version_is_last": true, "title": ["Data Collaboration Analysis Framework Using Centralization of Individual Intermediate Representations for Distributed Data Sets"], "weko_shared_id": 5}
Data Collaboration Analysis Framework Using Centralization of Individual Intermediate Representations for Distributed Data Sets
http://hdl.handle.net/2241/00160187
http://hdl.handle.net/2241/00160187c8339e4c-f9e6-4536-ae87-cd3dc09227b6
名前 / ファイル | ライセンス | アクション |
---|---|---|
ASCE-ASME-B_6-2 (1.4 MB)
|
Item type | Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2020-06-23 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Data Collaboration Analysis Framework Using Centralization of Individual Intermediate Representations for Distributed Data Sets | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源 | http://purl.org/coar/resource_type/c_6501 | |||||
タイプ | journal article | |||||
著者 |
今倉, 暁
× 今倉, 暁× 櫻井, 鉄也 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | This paper proposes a data collaboration analysis framework for distributed data sets. The proposed framework involves centralized machine learning while the original data sets and models remain distributed over a number of institutions. Recently, data has become larger and more distributed with decreasing costs of data collection. Centralizing distributed data sets and analyzing them as one data set can allow for novel insights and attainment of higher prediction performance than that of analyzing distributed data sets individually. However, it is generally difficult to centralize the original data sets because of a large data size or privacy concerns. This paper proposes a data collaboration analysis framework that does not involve sharing the original data sets to circumvent these difficulties. The proposed framework only centralizes intermediate representations constructed individually rather than the original data set. The proposed framework does not use privacy-preserving computations or model centralization. In addition, this paper proposes a practical algorithm within the framework. Numerical experiments reveal that the proposed method achieves higher recognition performance for artificial and real-world problems than individual analysis. | |||||
書誌情報 |
en : ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering 巻 6, 号 2, p. 04020018, 発行日 2020-06 |
|||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 2376-7642 | |||||
DOI | ||||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1061/AJRUA6.0001058 | |||||
権利 | ||||||
権利情報 | © ASCE | |||||
権利 | ||||||
権利情報 | This work is made available under the terms of the Creative Commons Attribution 4.0 International license, http://creativecommons.org/licenses/by/4.0/. | |||||
著者版フラグ | ||||||
値 | publisher | |||||
出版者 | ||||||
出版者 | American Society of Civil Engineers |