{"id":214304,"updated":"2025-01-19T16:49:46.510143+00:00","links":{},"created":"2025-01-19T01:15:07.640570+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214304","sets":["1164:2735:10526:10756"]},"path":["10756"],"owner":"44499","recid":"214304","title":["一対比較データと目的変数分布の分位数を用いた回帰モデルの学習"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-12-06"},"_buckets":{"deposit":"61d25004-f326-4af0-b84e-1df6ded6b723"},"_deposit":{"id":"214304","pid":{"type":"depid","value":"214304","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"一対比較データと目的変数分布の分位数を用いた回帰モデルの学習","author_link":["549437","549439","549438"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"一対比較データと目的変数分布の分位数を用いた回帰モデルの学習"},{"subitem_title":"Learning of Regression Models from Pairwise Data and Target Variable Quantiles","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2021-12-06","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"日本電信電話株式会社NTT人間情報研究所"},{"subitem_text_value":"日本電信電話株式会社NTT人間情報研究所"},{"subitem_text_value":"日本電信電話株式会社NTT人間情報研究所"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/214304/files/IPSJ-MPS21136007.pdf","label":"IPSJ-MPS21136007.pdf"},"date":[{"dateType":"Available","dateValue":"2023-12-06"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS21136007.pdf","filesize":[{"value":"1.5 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"ba6391e4-ca0d-4a2e-a85d-469ff0c0e2fb","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"南部, 優太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"幸島, 匡宏"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山本, 隆二"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8833","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"画像や音声の品質評価や感情推定のために収集されたデータ，プライバシ保護のために加工されたアンケート回答データなどは，2 つのサンプルの目的変数の順序関係 (画像の品質の高さや被験者の感情の大きさ，アンケート回答者の年収の順序など) を表す一対比較データの形式でしばしば与えられる．このデータから任意のサンプルの大小関係を予測するモデルを学習することが目標である場合，既存の様々なランキング学習の手法を利用することが可能である．しかしながら，データ中に目的変数の値そのものは記録されていないため，これらの手法を用いても目的変数を予測する回帰モデルを学習することはできなかった．そこで本研究は，目的変数の周辺分布の分位数に関する情報が利用可能であるという条件のもと (品質/感情の大きさの 5 段階評価で，画像全体の 50% は評価値 3 以下, 被験者の 75% は評価値 4 以下など)，一対比較データから回帰モデルを学習する新しい手法を提案する．提案手法はランキング学習の損失関数とモデルの出力する目的変数の分布の分位数を用いて計算される正則化項の和を最小化することでモデルのパラメタを推定する．人工データ及び実データを用いた実験により提案手法の有用性を検証した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-12-06","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"7","bibliographicVolumeNumber":"2021-MPS-136"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}