{"id":"https://openalex.org/W3196436244","doi":"https://doi.org/10.14778/3476311.3476333","title":"Automatic data acquisition for deep learning","display_name":"Automatic data acquisition for deep learning","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3196436244","doi":"https://doi.org/10.14778/3476311.3476333","mag":"3196436244"},"language":"en","primary_location":{"id":"doi:10.14778/3476311.3476333","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476333","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5100659171","display_name":"Jiabin Liu","orcid":"https://orcid.org/0000-0001-6914-8941"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabin Liu","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029626005","display_name":"Fu Zhu","orcid":"https://orcid.org/0000-0002-8059-8991"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Zhu","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797040","display_name":"Chengliang Chai","orcid":"https://orcid.org/0000-0001-8080-5594"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengliang Chai","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614732","display_name":"Yuyu Luo","orcid":"https://orcid.org/0000-0001-9530-3327"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyu Luo","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[{"id":"https://openalex.org/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["QCRI, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QCRI, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6378,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86496017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"14","issue":"12","first_page":"2739","last_page":"2742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/T12535","display_name":"Machine Learning and Data Classification","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7347782850265503},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6737706661224365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5604948401451111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.558210551738739},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5422682166099548},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48606374859809875},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.471706360578537},{"id":"https://openalex.org/keywords/data-acquisition","display_name":"Data acquisition","score":0.4640148878097534},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4495866298675537},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.41631269454956055},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4132893681526184},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4111669957637787},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3435690402984619},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09188738465309143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347782850265503},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6737706661224365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5604948401451111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.558210551738739},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5422682166099548},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48606374859809875},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.471706360578537},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.4640148878097534},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4495866298675537},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.41631269454956055},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4132893681526184},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4111669957637787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3435690402984619},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09188738465309143},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3476311.3476333","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476333","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2428834396","https://openalex.org/W2597603852","https://openalex.org/W2769041395","https://openalex.org/W2795117410","https://openalex.org/W2795226127","https://openalex.org/W2798664493","https://openalex.org/W2808345493","https://openalex.org/W2952821957","https://openalex.org/W2959716049","https://openalex.org/W2963265099","https://openalex.org/W2996500300","https://openalex.org/W2999324038","https://openalex.org/W3006978394","https://openalex.org/W3030764521","https://openalex.org/W3128279037","https://openalex.org/W3174906424","https://openalex.org/W6750219672"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"Deep":[0],"learning":[1,14,166],"(DL)":[2],"has":[3,7],"widespread":[4],"applications":[5],"and":[6,65,95,123,182,193,205],"revolutionized":[8],"many":[9,40,51],"industries.":[10],"Although":[11],"automated":[12],"machine":[13],"(AutoML)":[15],"can":[16,212],"help":[17],"us":[18],"away":[19],"from":[20,91,118,138],"coding":[21],"for":[22,32,39,142],"DL":[23,41,145],"models,":[24],"the":[25,156,173,218],"acquisition":[26,111],"of":[27,29,87,184],"lots":[28],"high-quality":[30,136,214],"data":[31,66,73,89,96,110,117,121,137,181,207,215],"model":[33],"training":[34,80,88,116,180],"remains":[35],"a":[36,85,106,119,139,143,164,187],"main":[37,130],"bottleneck":[38],"projects,":[42],"simply":[43],"because":[44],"it":[45],"requires":[46],"high":[47],"human":[48],"cost.":[49],"Despite":[50],"works":[52],"on":[53,75],"weak":[54,60],"supervision":[55],"(":[56,68],"i.e.":[57,69],",":[58,70],"adding":[59],"labels":[61],"to":[62,134,154,171,189,216],"seen":[63,76],"data)":[64],"augmentation":[67],"generating":[71],"more":[72],"based":[74],"data),":[77],"automatically":[78,114],"acquiring":[79],"data,":[81,192],"via":[82],"smartly":[83],"searching":[84],"pool":[86],"collected":[90],"open":[92],"ML":[93],"benchmarks":[94],"markets,":[97],"is":[98],"not":[99],"explored.":[100],"In":[101],"this":[102],"demonstration,":[103],"we":[104,162],"demonstrate":[105,198],"new":[107],"system,":[108],"automatic":[109],"(AutoData),":[112],"which":[113],"searches":[115],"heterogeneous":[120],"repository":[122,141],"interacts":[124],"with":[125,152,199],"AutoML.":[126],"It":[127],"faces":[128],"two":[129,200],"challenges.":[131],"(1)":[132],"How":[133,148],"search":[135,175,190],"large":[140],"given":[144],"task?":[146],"(2)":[147],"does":[149],"AutoData":[150,170,177,211],"interact":[151],"AutoML":[153],"guide":[155,172],"search?":[157],"To":[158],"address":[159],"these":[160],"challenges,":[161],"propose":[163],"reinforcement":[165],"(RL)-based":[167],"framework":[168],"in":[169,195],"iterative":[174],"process.":[176],"encodes":[178],"current":[179],"feedbacks":[183],"AutoML,":[185],"learns":[186],"policy":[188],"fresh":[191],"trains":[194],"iterations.":[196],"We":[197],"real-life":[201],"scenarios,":[202],"image":[203],"classification":[204],"relational":[206],"prediction,":[208],"showing":[209],"that":[210],"select":[213],"improve":[217],"model.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}