{"id":"https://openalex.org/W7138936745","doi":"https://doi.org/10.1016/j.neucom.2026.133405","title":"Optimizing pre-training for multi-label classification via generalized target-aware source data selection","display_name":"Optimizing pre-training for multi-label classification via generalized target-aware source data selection","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7138936745","doi":"https://doi.org/10.1016/j.neucom.2026.133405"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133405","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133405","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2026.133405","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113348797","display_name":"Kanyu Miyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kanyu Miyoshi","raw_affiliation_strings":["Graduate School of Creative Science and Engineering, Waseda University, 3-4-1 Ohkubo, Shinjuku-ku, 169-8555, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0006-6168-1067","affiliations":[{"raw_affiliation_string":"Graduate School of Creative Science and Engineering, Waseda University, 3-4-1 Ohkubo, Shinjuku-ku, 169-8555, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130036283","display_name":"Ryotaro Shimizu","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryotaro Shimizu","raw_affiliation_strings":["Institute of Data Science, Waseda University, 3-4-1 Ohkubo, Shinjuku-ku, 169-8555, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4841-1824","affiliations":[{"raw_affiliation_string":"Institute of Data Science, Waseda University, 3-4-1 Ohkubo, Shinjuku-ku, 169-8555, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130106524","display_name":"Linxin Song","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linxin Song","raw_affiliation_strings":["Thomas Lord Department of Computer Science, University of Southern California, Salvatori Computer Science Center (SAL), 941 Bloom Walk, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thomas Lord Department of Computer Science, University of Southern California, Salvatori Computer Science Center (SAL), 941 Bloom Walk, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004873494","display_name":"Masayuki Goto","orcid":"https://orcid.org/0000-0003-1929-9359"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Goto","raw_affiliation_strings":["School of Creative Science and Engineering, Waseda University, 3-4-1 Ohkubo, Shinjuku-ku, 169-8555, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Creative Science and Engineering, Waseda University, 3-4-1 Ohkubo, Shinjuku-ku, 169-8555, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5130036283"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":{"value":2470,"currency":"USD","value_usd":2470},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57984313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"681","issue":null,"first_page":"133405","last_page":"133405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.7303000092506409,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.7303000092506409,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.04659999907016754,"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/T10057","display_name":"Face and Expression Recognition","score":0.0340999998152256,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4844000041484833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4593000113964081},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.39890000224113464},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.28349998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5163999795913696},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2780724565","wikidata":"https://www.wikidata.org/wiki/Q5227256","display_name":"Data classification","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133405","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133405","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2026.133405","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133405","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2277195237","https://openalex.org/W4200334431","https://openalex.org/W4223611486","https://openalex.org/W4288083516","https://openalex.org/W4288758332","https://openalex.org/W4308432165","https://openalex.org/W4313491434","https://openalex.org/W4384563227","https://openalex.org/W4385780033","https://openalex.org/W4385986816","https://openalex.org/W4386002638","https://openalex.org/W4387472633","https://openalex.org/W4388208979","https://openalex.org/W4388840685","https://openalex.org/W4389113716","https://openalex.org/W4389160174","https://openalex.org/W4389352201","https://openalex.org/W4389827858","https://openalex.org/W4389955489","https://openalex.org/W4390323078","https://openalex.org/W4390619961","https://openalex.org/W4391070541","https://openalex.org/W4391093457","https://openalex.org/W4391221083","https://openalex.org/W4391238866","https://openalex.org/W4391473819","https://openalex.org/W4391771706","https://openalex.org/W4391838344","https://openalex.org/W4392143739","https://openalex.org/W4392453506","https://openalex.org/W4392768458","https://openalex.org/W4392883826","https://openalex.org/W4393318957","https://openalex.org/W4394770269","https://openalex.org/W4394789421","https://openalex.org/W4395014896","https://openalex.org/W4395447967","https://openalex.org/W4396768678","https://openalex.org/W4396920624","https://openalex.org/W4396941381","https://openalex.org/W4397010262","https://openalex.org/W4399882764","https://openalex.org/W4400016580","https://openalex.org/W4400079774","https://openalex.org/W4400391711","https://openalex.org/W4400424831","https://openalex.org/W4400798277","https://openalex.org/W4401026360","https://openalex.org/W4401405048","https://openalex.org/W4401558836","https://openalex.org/W4401567990","https://openalex.org/W4401672000","https://openalex.org/W4401691622","https://openalex.org/W4402492178","https://openalex.org/W4402568864","https://openalex.org/W4402787732","https://openalex.org/W4404328104","https://openalex.org/W4404803706","https://openalex.org/W4405316148","https://openalex.org/W4405765307","https://openalex.org/W4413890170"],"related_works":[],"abstract_inverted_index":{"While":[0],"pre-trained":[1,201,225],"models,":[2,7,226],"such":[3,249],"as":[4,250],"large":[5],"language":[6],"can":[8,28],"achieve":[9],"high":[10],"performance":[11,30,43,210,270],"with":[12,159,245],"minimal":[13],"fine-tuning,":[14],"the":[15,65,85,198,228],"source":[16,39,47,139,169,189,205,233,292],"datasets":[17,151],"used":[18],"for":[19,141,211,243,260],"pre-training":[20,45],"often":[21],"contain":[22],"irrelevant":[23,188],"or":[24,174],"blackundant":[25],"data,":[26,132,248],"which":[27],"degrade":[29],"on":[31,46,51,130,144,224],"target":[32,57,131,171,213,268,288],"tasks.":[33,78,214],"Domain":[34],"Adaptation":[35],"Information":[36],"Gain":[37],"(DAIG)-based":[38],"data":[40,48,58,140,206,257,274,289,293],"selection":[41,89,258],"improves":[42,267],"by":[44,187],"selected":[49],"based":[50],"rough":[52],"prior":[53,125],"knowledge":[54],"obtained":[55],"from":[56,127,184,287],"in":[59,163],"advance.":[60],"However,":[61],"DAIG\u2019s":[62],"key":[63],"component,":[64],"transition":[66,105,279],"matrix,":[67],"lacks":[68],"flexibility":[69],"and":[70,111,137,147,170,240],"is":[71,263],"limited":[72],"to":[73,97,107,116,119,196],"handling":[74],"only":[75],"single-label":[76],"classification":[77,150,262],"To":[79],"address":[80],"this":[81],"limitation,":[82],"we":[83],"propose":[84],"Generalized":[86],"DAIG":[87,96],"(GDAIG)-guided":[88],"process,":[90],"a":[91,103,238],"novel":[92],"framework":[93,216],"that":[94,153,221],"extends":[95],"support":[98],"multi-label":[99,120,261,273,302],"classification.":[100],"GDAIG":[101,133,154,236,266,296],"introduces":[102],"soft":[104],"matrix":[106,280],"capture":[108],"inter-label":[109,282],"dependencies":[110],"employs":[112],"binary":[113],"cross-entropy":[114],"loss":[115],"enable":[117],"adaptation":[118],"data.":[121,234],"By":[122],"leveraging":[123],"\u201crough":[124],"knowledge\u201d":[126],"initial":[128],"training":[129],"actively":[134],"selects":[135],"informative":[136],"task-relevant":[138,232,272],"pre-training.":[142,294],"Experiments":[143],"medical":[145,251],"image":[146,252],"general":[148],"object":[149],"demonstrate":[152],"consistently":[155],"outperforms":[156,297],"baseline":[157],"approaches,":[158],"particularly":[160],"significant":[161],"improvements":[162],"scenarios":[164],"involving":[165],"label":[166,176],"mismatch":[167],"between":[168],"domains":[172,244],"(partial":[173],"no":[175],"overlap),":[177],"where":[178],"conventional":[179,298],"transfer":[180],"learning":[181],"methods":[182],"suffer":[183],"noise":[185],"caused":[186],"labels.":[190],"These":[191],"results":[192],"highlight":[193],"GDAIG\u2019s":[194],"ability":[195],"enhance":[197],"effectiveness":[199],"of":[200,231],"models":[202],"through":[203,271],"strategic":[204],"selection,":[207],"thereby":[208],"optimizing":[209],"specific":[212],"Our":[215],"goes":[217],"beyond":[218],"existing":[219],"approaches":[220],"rely":[222],"solely":[223],"emphasizing":[227],"direct":[229],"utilization":[230],"Furthermore,":[235],"provides":[237],"practical":[239],"effective":[241],"solution":[242],"scarce":[246],"labeled":[247],"analysis.":[253],"\u2022":[254,265,276,284,295],"A":[255,277],"GDAIG-guided":[256],"strategy":[259],"proposed.":[264],"model":[269],"selection.":[275],"probabilistic":[278],"captures":[281],"dependencies.":[283],"\u201cRough":[285],"prior\u201d":[286],"effectively":[290],"guides":[291],"baselines":[299],"across":[300],"diverse":[301],"scenarios.":[303]},"counts_by_year":[],"updated_date":"2026-03-24T05:59:24.953642","created_date":"2026-03-20T00:00:00"}