{"id":"https://openalex.org/W2929941791","doi":"https://doi.org/10.1145/3299869.3319888","title":"HoloDetect","display_name":"HoloDetect","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2929941791","doi":"https://doi.org/10.1145/3299869.3319888","mag":"2929941791"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3319888","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3319888","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3319888","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3319888","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alireza Heidari","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Alireza Heidari","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joshua McGrath","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua McGrath","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ihab F. Ilyas","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ihab F. Ilyas","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":null,"display_name":"Theodoros Rekatsinas","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theodoros Rekatsinas","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":5.7806,"has_fulltext":true,"cited_by_count":103,"citation_normalized_percentile":{"value":0.96767198,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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":0.9994000196456909,"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/key","display_name":"Key (lock)","score":0.6385999917984009},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.47099998593330383},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46970000863075256},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4350000023841858},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.3562000095844269},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35370001196861267},{"id":"https://openalex.org/keywords/semantic-heterogeneity","display_name":"Semantic heterogeneity","score":0.34139999747276306},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.33559998869895935},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.32670000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049000263214111},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6385999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5932000279426575},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.34139999747276306},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3299869.3319888","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3319888","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3319888","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.02285","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.02285","pdf_url":"https://arxiv.org/pdf/1904.02285","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3299869.3319888","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3319888","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3319888","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1848699955","display_name":null,"funder_award_id":"1755676","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2862252062","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G4610349057","display_name":null,"funder_award_id":"IIS-1755676","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321487","display_name":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2929941791.pdf","grobid_xml":"https://content.openalex.org/works/W2929941791.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W571200655","https://openalex.org/W1499253590","https://openalex.org/W1976732638","https://openalex.org/W1983170052","https://openalex.org/W1992479406","https://openalex.org/W2019858993","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047182010","https://openalex.org/W2047745978","https://openalex.org/W2053724458","https://openalex.org/W2064766209","https://openalex.org/W2078132546","https://openalex.org/W2099637074","https://openalex.org/W2130858665","https://openalex.org/W2163922914","https://openalex.org/W2170712852","https://openalex.org/W2190899134","https://openalex.org/W2194775991","https://openalex.org/W2213275763","https://openalex.org/W2295468252","https://openalex.org/W2427822648","https://openalex.org/W2475334473","https://openalex.org/W2493916176","https://openalex.org/W2544486974","https://openalex.org/W2591700809","https://openalex.org/W2614592379","https://openalex.org/W2669032454","https://openalex.org/W2769041395","https://openalex.org/W2798323405","https://openalex.org/W2884424959","https://openalex.org/W2889005129","https://openalex.org/W2951559648","https://openalex.org/W3000214033","https://openalex.org/W3028454718","https://openalex.org/W4293582904"],"related_works":[],"abstract_inverted_index":{"We":[0,9,99,132,155],"introduce":[1],"a":[2,59,65,95,119,137],"few-shot":[3],"learning":[4,153],"framework":[5,34,103],"for":[6],"error":[7,25,141],"detection.":[8],"show":[10,100,156],"that":[11,28,47,101,124,157],"data":[12,60,86,158],"augmentation":[13,61,87,159],"(a":[14],"form":[15],"of":[16,36,55,68,110,116,122,130,140,164],"weak":[17],"supervision)":[18],"is":[19,83],"key":[20,81],"to":[21,43,74,84,136,149,172,178],"training":[22,78],"high-quality,":[23],"ML-based":[24],"detection":[26,142],"models":[27],"require":[29],"minimal":[30],"human":[31],"involvement.":[32],"Our":[33,80],"consists":[35],"two":[37],"parts:":[38],"(1)":[39],"an":[40,107,113,161],"expressive":[41],"model":[42,62],"learn":[44,85],"rich":[45],"representations":[46],"capture":[48],"the":[49,90],"inherent":[50],"syntactic":[51],"and":[52,57,112,128,151],"semantic":[53],"heterogeneity":[54],"errors;":[56],"(2)":[58],"that,":[63],"given":[64],"small":[66],"seed":[67],"clean":[69],"records,":[70],"uses":[71],"dataset-specific":[72],"transformations":[73],"automatically":[75],"generate":[76],"additional":[77],"data.":[79],"insight":[82],"policies":[88],"from":[89,145],"noisy":[91],"input":[92],"dataset":[93],"in":[94],"weakly":[96],"supervised":[97],"manner.":[98],"our":[102,134],"detects":[104],"errors":[105],"with":[106],"average":[108,114,162],"precision":[109],"~94%":[111],"recall":[115],"~93%":[117],"across":[118],"diverse":[120],"array":[121],"datasets":[123],"exhibit":[125],"different":[126],"types":[127],"amounts":[129],"errors.":[131],"compare":[133],"approach":[135],"comprehensive":[138],"collection":[139],"methods,":[143],"ranging":[144],"traditional":[146],"rule-based":[147],"methods":[148],"ensemble-based":[150],"active":[152],"approaches.":[154,181],"yields":[160],"improvement":[163],"20":[165],"F1":[166],"points":[167],"while":[168],"it":[169],"requires":[170],"access":[171],"3x":[173],"fewer":[174],"labeled":[175],"examples":[176],"compared":[177],"other":[179],"ML":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2019-04-11T00:00:00"}