{"id":"https://openalex.org/W3172485152","doi":"https://doi.org/10.1145/3447548.3467409","title":"Improve Learning from Crowds via Generative Augmentation","display_name":"Improve Learning from Crowds via Generative Augmentation","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3172485152","doi":"https://doi.org/10.1145/3447548.3467409","mag":"3172485152"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.10449","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhendong Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhendong Chu","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hongning Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongning Wang","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.9736,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80096835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9965000152587891,"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":0.9930999875068665,"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/crowds","display_name":"Crowds","score":0.8499000072479248},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.8489999771118164},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6324999928474426},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.569100022315979},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5353999733924866},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3971000015735626},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.8499000072479248},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.8489999771118164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6455000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6399999856948853},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3971000015735626},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3686000108718872},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C197352329","wikidata":"https://www.wikidata.org/wiki/Q1093434","display_name":"Citizen science","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3447548.3467409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.10449","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.10449","pdf_url":"https://arxiv.org/pdf/2107.10449","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"},{"id":"pmh:oai:osti.gov:1822655","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1822655","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.10449","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.10449","pdf_url":"https://arxiv.org/pdf/2107.10449","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5718332806","display_name":null,"funder_award_id":"1718216,1553568","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7730204185","display_name":null,"funder_award_id":"EE0008227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W2091759811","https://openalex.org/W2110764733","https://openalex.org/W2141649520","https://openalex.org/W2142518823","https://openalex.org/W2180771322","https://openalex.org/W2329105431","https://openalex.org/W2619206542","https://openalex.org/W2897167574","https://openalex.org/W2950166131","https://openalex.org/W2963169753","https://openalex.org/W2963772355","https://openalex.org/W2979302305","https://openalex.org/W3003609932","https://openalex.org/W3005295611","https://openalex.org/W4293409613"],"related_works":[],"abstract_inverted_index":{"Crowdsourcing":[0],"provides":[1],"an":[2,122,130],"efficient":[3],"label":[4],"collection":[5],"schema":[6],"for":[7,157],"supervised":[8],"machine":[9,41],"learning.":[10],"However,":[11],"to":[12,54,66],"control":[13],"annotation":[14],"cost,":[15],"each":[16],"instance":[17],"in":[18,57,160],"the":[19,38,73,89,94,106,115,143,152],"crowdsourced":[20,58],"data":[21,59,61,147],"is":[22,100,119],"typically":[23],"annotated":[24],"by":[25,71,102,121],"a":[26,33,69,103],"small":[27],"number":[28],"of":[29,40,81,96,132,145,154],"annotators.":[30],"This":[31],"creates":[32],"sparsity":[34,56],"issue":[35],"and":[36,127],"limits":[37],"quality":[39],"learning":[42,134],"models":[43],"trained":[44],"on":[45,138],"such":[46],"data.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,64],"study":[52],"how":[53],"handle":[55],"using":[60,84],"augmentation.":[62],"Specifically,":[63],"propose":[65],"directly":[67],"learn":[68],"classifier":[70],"augmenting":[72],"raw":[74],"sparse":[75],"annotations.":[76],"We":[77],"implement":[78],"two":[79],"principles":[80],"high-quality":[82],"augmentation":[83,148],"Generative":[85],"Adversarial":[86],"Networks:":[87],"1)":[88],"generated":[90,107],"annotations":[91,108],"should":[92,109],"follow":[93],"distribution":[95],"authentic":[97],"ones,":[98],"which":[99,118],"measured":[101,120],"discriminator;":[104],"2)":[105],"have":[110],"high":[111],"mutual":[112],"information":[113],"with":[114],"ground-truth":[116],"labels,":[117],"auxiliary":[123],"network.":[124],"Extensive":[125],"experiments":[126],"comparisons":[128],"against":[129],"array":[131],"state-of-the-art":[133],"from":[135],"crowds":[136],"methods":[137],"three":[139],"real-world":[140],"datasets":[141],"proved":[142],"effectiveness":[144],"our":[146,155],"framework.":[149],"It":[150],"shows":[151],"potential":[153],"algorithm":[156],"low-budget":[158],"crowdsourcing":[159],"general.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2021-06-22T00:00:00"}