{"id":"https://openalex.org/W3198440572","doi":"https://doi.org/10.14778/3476311.3476403","title":"Data augmentation for ML-driven data preparation and integration","display_name":"Data augmentation for ML-driven data preparation and integration","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3198440572","doi":"https://doi.org/10.14778/3476311.3476403","mag":"3198440572"},"language":"en","primary_location":{"id":"doi:10.14778/3476311.3476403","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476403","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/A5100750716","display_name":"Yuliang Li","orcid":"https://orcid.org/0000-0002-0602-149X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuliang Li","raw_affiliation_strings":["Megagon Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767232","display_name":"Xiaolan Wang","orcid":"https://orcid.org/0000-0003-3846-1753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolan Wang","raw_affiliation_strings":["Megagon Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087858861","display_name":"Zhengjie Miao","orcid":"https://orcid.org/0009-0008-2371-1186"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengjie Miao","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026007789","display_name":"Wang-Chiew Tan","orcid":"https://orcid.org/0009-0008-4174-7545"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Wang-Chiew Tan","raw_affiliation_strings":["Facebook AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0473,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88962263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"12","first_page":"3182","last_page":"3185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9976999759674072,"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":0.9976999759674072,"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/T11719","display_name":"Data Quality and Management","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/leverage","display_name":"Leverage (statistics)","score":0.7822421789169312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7501477599143982},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5298359990119934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.470355749130249},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4510672092437744},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44230079650878906},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4308682084083557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43066030740737915},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23378819227218628},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11299553513526917},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09586817026138306}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7822421789169312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501477599143982},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5298359990119934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.470355749130249},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4510672092437744},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44230079650878906},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4308682084083557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43066030740737915},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23378819227218628},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11299553513526917},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09586817026138306}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3476311.3476403","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476403","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1870305865","https://openalex.org/W1992479406","https://openalex.org/W2044469685","https://openalex.org/W2080757240","https://openalex.org/W2099471712","https://openalex.org/W2102162869","https://openalex.org/W2108267498","https://openalex.org/W2143124645","https://openalex.org/W2150365753","https://openalex.org/W2182787248","https://openalex.org/W2509340590","https://openalex.org/W2612824201","https://openalex.org/W2751134959","https://openalex.org/W2765407302","https://openalex.org/W2769041395","https://openalex.org/W2775795276","https://openalex.org/W2798578675","https://openalex.org/W2798649495","https://openalex.org/W2803751389","https://openalex.org/W2804269561","https://openalex.org/W2806276686","https://openalex.org/W2810075754","https://openalex.org/W2905266130","https://openalex.org/W2911424454","https://openalex.org/W2911588830","https://openalex.org/W2929941791","https://openalex.org/W2943305281","https://openalex.org/W2946504770","https://openalex.org/W2948145720","https://openalex.org/W2949736877","https://openalex.org/W2951147191","https://openalex.org/W2953289575","https://openalex.org/W2959716049","https://openalex.org/W2964087600","https://openalex.org/W2970418174","https://openalex.org/W2971252690","https://openalex.org/W2971681342","https://openalex.org/W2977218433","https://openalex.org/W2985009327","https://openalex.org/W2998184481","https://openalex.org/W3004437239","https://openalex.org/W3004612262","https://openalex.org/W3010144884","https://openalex.org/W3010293452","https://openalex.org/W3013103751","https://openalex.org/W3014705052","https://openalex.org/W3018652502","https://openalex.org/W3035542229","https://openalex.org/W3035682985","https://openalex.org/W3037878364","https://openalex.org/W3047916742","https://openalex.org/W3082181878","https://openalex.org/W3082197983","https://openalex.org/W3085364681","https://openalex.org/W3094176124","https://openalex.org/W3101980583","https://openalex.org/W3102631365","https://openalex.org/W3103177583","https://openalex.org/W3104182623","https://openalex.org/W3105771849","https://openalex.org/W3105977086","https://openalex.org/W3106031848","https://openalex.org/W3110608319","https://openalex.org/W3115908473","https://openalex.org/W3123375411","https://openalex.org/W3123788974","https://openalex.org/W3142774214","https://openalex.org/W3165814564","https://openalex.org/W3174036215"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W2275805942","https://openalex.org/W4381280689","https://openalex.org/W3033859939","https://openalex.org/W2847365777","https://openalex.org/W2355048207","https://openalex.org/W3126051647","https://openalex.org/W2961085424","https://openalex.org/W3098003361"],"abstract_inverted_index":{"In":[0,25,48],"recent":[1],"years,":[2],"we":[3,28,67,84],"have":[4],"witnessed":[5],"the":[6,38,70,86],"development":[7],"of":[8,34],"novel":[9],"data":[10,18,39,43,46,118],"augmentation":[11,119],"(DA)":[12],"techniques":[13,35,73],"for":[14,42,62,115,121],"creating":[15,63],"additional":[16,64],"training":[17,65],"needed":[19],"by":[20,37],"machine":[21,92],"learning":[22,93],"based":[23],"solutions.":[24],"this":[26,106],"tutorial,":[27],"will":[29],"provide":[30],"a":[31,116],"comprehensive":[32],"overview":[33],"developed":[36],"management":[40],"community":[41],"preparation":[44],"and":[45,59,79,90,100],"integration.":[47],"addition":[49],"to":[50],"surveying":[51],"task-specific":[52],"DA":[53,72,80,89],"operators":[54],"that":[55,105],"leverage":[56],"rules,":[57],"transformations,":[58],"external":[60],"knowledge":[61],"data,":[66],"also":[68],"explore":[69],"advanced":[71],"such":[74,95],"as":[75,96],"interpolation,":[76],"conditional":[77],"generation,":[78],"policy":[81],"learning.":[82,102],"Finally,":[83],"describe":[85],"connection":[87],"between":[88],"other":[91],"paradigms":[94],"active":[97],"learning,":[98],"pre-training,":[99],"weakly-supervised":[101],"We":[103],"hope":[104],"discussion":[107],"can":[108],"shed":[109],"light":[110],"on":[111],"future":[112],"research":[113],"directions":[114],"holistic":[117],"framework":[120],"high-quality":[122],"dataset":[123],"creation.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}