{"id":"https://openalex.org/W3128750371","doi":"https://doi.org/10.1109/tnnls.2021.3053633","title":"Optimizing Attention for Sequence Modeling via Reinforcement Learning","display_name":"Optimizing Attention for Sequence Modeling via Reinforcement Learning","publication_year":2021,"publication_date":"2021-02-12","ids":{"openalex":"https://openalex.org/W3128750371","doi":"https://doi.org/10.1109/tnnls.2021.3053633","mag":"3128750371","pmid":"https://pubmed.ncbi.nlm.nih.gov/33566767"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3053633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3053633","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055815455","display_name":"Hao Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Fei","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055938662","display_name":"Yafeng Ren","orcid":"https://orcid.org/0000-0002-0291-4733"},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafeng Ren","raw_affiliation_strings":["School of Interpreting and Translation, Guangdong University of Foreign Studies, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Interpreting and Translation, Guangdong University of Foreign Studies, Guangzhou, China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058877618","display_name":"Donghong Ji","orcid":"https://orcid.org/0000-0001-9613-5927"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghong Ji","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055815455"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":3.6711,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94022329,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"33","issue":"8","first_page":"3612","last_page":"3621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7561156749725342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510743141174316},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.691835343837738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.678758978843689},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6142784953117371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5370392203330994},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.42326128482818604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08382466435432434},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.07022315263748169},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06336095929145813}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7561156749725342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510743141174316},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.691835343837738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.678758978843689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6142784953117371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5370392203330994},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.42326128482818604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08382466435432434},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.07022315263748169},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06336095929145813},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3053633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3053633","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:33566767","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33566767","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1588465053","display_name":null,"funder_award_id":"18JZD015","funder_id":"https://openalex.org/F4320336751","funder_display_name":"Science Foundation of Ministry of Education of China"},{"id":"https://openalex.org/G6442732870","display_name":null,"funder_award_id":"61772378","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6595826518","display_name":null,"funder_award_id":"61702121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336751","display_name":"Science Foundation of Ministry of Education of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1832693441","https://openalex.org/W1902237438","https://openalex.org/W2024390895","https://openalex.org/W2064675550","https://openalex.org/W2114524997","https://openalex.org/W2119717200","https://openalex.org/W2133564696","https://openalex.org/W2163455955","https://openalex.org/W2551396370","https://openalex.org/W2562607067","https://openalex.org/W2563010554","https://openalex.org/W2604205681","https://openalex.org/W2625720409","https://openalex.org/W2757154661","https://openalex.org/W2782276075","https://openalex.org/W2785128315","https://openalex.org/W2805151692","https://openalex.org/W2807741081","https://openalex.org/W2808182015","https://openalex.org/W2895944290","https://openalex.org/W2950768109","https://openalex.org/W2952028139","https://openalex.org/W2952406142","https://openalex.org/W2952802110","https://openalex.org/W2962729168","https://openalex.org/W2963051485","https://openalex.org/W2963467630","https://openalex.org/W2963499882","https://openalex.org/W2963696295","https://openalex.org/W2963813679","https://openalex.org/W2963888230","https://openalex.org/W2963963856","https://openalex.org/W2964005754","https://openalex.org/W2964164368","https://openalex.org/W2964189376","https://openalex.org/W2964268978","https://openalex.org/W2970120757","https://openalex.org/W2970726176","https://openalex.org/W2971044268","https://openalex.org/W2971351900","https://openalex.org/W2977700998","https://openalex.org/W2989149555","https://openalex.org/W2997003477","https://openalex.org/W2997087088","https://openalex.org/W3034444624","https://openalex.org/W3104213339","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685053522","https://openalex.org/W6691459498","https://openalex.org/W6729383884","https://openalex.org/W6729654139","https://openalex.org/W6738577479","https://openalex.org/W6738908108","https://openalex.org/W6739901393","https://openalex.org/W6764072591"],"related_works":["https://openalex.org/W2364252372","https://openalex.org/W4234066492","https://openalex.org/W4362501864","https://openalex.org/W1998063895","https://openalex.org/W4306904969","https://openalex.org/W3011059803","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W1967044713","https://openalex.org/W2031695474"],"abstract_inverted_index":{"Attention":[0],"has":[1],"been":[2],"shown":[3],"highly":[4],"effective":[5],"for":[6,128],"modeling":[7],"sequences,":[8],"capturing":[9],"the":[10,24,57,104],"more":[11,65,79,83,109,114],"informative":[12,80],"parts":[13],"in":[14,33,102],"learning":[15,50],"a":[16],"deep":[17,48],"representation.":[18],"However,":[19],"recent":[20],"studies":[21],"show":[22],"that":[23,78,95,119],"attention":[25,54,75,84,92,111],"values":[26],"do":[27],"not":[28],"always":[29],"coincide":[30],"with":[31],"intuition":[32],"tasks,":[34],"such":[35],"as":[36],"machine":[37],"translation":[38],"and":[39,90],"sentiment":[40],"classification.":[41],"In":[42],"this":[43],"study,":[44],"we":[45],"consider":[46],"using":[47],"reinforcement":[49],"to":[51,73,125],"automatically":[52],"optimize":[53],"distribution":[55],"during":[56],"minimization":[58],"of":[59,99],"end":[60,105],"task":[61,106],"training":[62],"losses.":[63],"With":[64],"sufficient":[66],"environment":[67],"states,":[68],"iterative":[69],"actions":[70],"are":[71],"taken":[72],"adjust":[74],"weights":[76],"so":[77],"words":[81],"receive":[82],"automatically.":[85],"Results":[86],"on":[87],"different":[88,91],"tasks":[89],"networks":[93],"demonstrate":[94],"our":[96,120],"model":[97],"is":[98],"great":[100],"effectiveness":[101],"improving":[103],"performances,":[107],"yielding":[108],"reasonable":[110],"distribution.":[112],"The":[113],"in-depth":[115],"analysis":[116],"further":[117],"reveals":[118],"retrofitting":[121],"method":[122],"can":[123],"help":[124],"bring":[126],"explainability":[127],"baseline":[129],"attention.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
