{"created":"2025-01-19T01:17:59.465063+00:00","updated":"2025-01-19T15:28:29.751855+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217500","sets":["1164:2240:10902:10903"]},"path":["10903"],"owner":"44499","recid":"217500","title":["グラフニューラルネットワークによる長時間分子動力学予測と性能評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-10"},"_buckets":{"deposit":"92fe4863-b00d-44c3-923b-1731a589a59e"},"_deposit":{"id":"217500","pid":{"type":"depid","value":"217500","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"グラフニューラルネットワークによる長時間分子動力学予測と性能評価","author_link":["563671","563670","563673","563672"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"グラフニューラルネットワークによる長時間分子動力学予測と性能評価"},{"subitem_title":"Graph Neural Networks Prediction of Long-Time Molecular Dynamics and its Benchmarks","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"高性能計算","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-10","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学情報基盤センター"},{"subitem_text_value":"東京大学情報基盤センター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Information Technology Center, University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Information Technology Center, University of Tokyo","subitem_text_language":"en"}]},"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/217500/files/IPSJ-HPC22183022.pdf","label":"IPSJ-HPC22183022.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-10"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HPC22183022.pdf","filesize":[{"value":"2.8 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":"14"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"41228136-908b-41e6-af76-b88c4de77505","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"芝, 隼人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"下川辺, 隆史"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hayato, Shiba","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takashi, Shimokawabe","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10463942","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":"2188-8841","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"分子動力学シミュレーションは，所与の物理系の構成要素である原子分子をその運動方程式に従って運動させることによって物質の性質を予言する強力な手法としての位置を確立している．しかし，長時間の分子動力学の時間積分にについては演算器のクロックサイクルによってその速度が制限され，1 日あたり 1010 ステップ数を超えるような長時間の計算は今後も困難である可能性が高い．最近，グラフニューラルネットワークが何万ステップ以上を隔てたステップ数の分子動力学の結果を良く予測することが見出された．この予測手法を用いることで分子動力学シミュレーションの適用対象を飛躍的に広げられる潜在的可能性を持っている．本発表では，このアプローチに対する我々の現在の取り組みを紹介するとともに，GPU (Graphics Processing Units) におけるグラフニューラルネットワークによる学習性能の評価を実施する．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"11","bibliographic_titles":[{"bibliographic_title":"研究報告ハイパフォーマンスコンピューティング（HPC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-10","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"22","bibliographicVolumeNumber":"2022-HPC-183"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217500,"links":{}}