{"id":"https://openalex.org/W2108740451","doi":"https://doi.org/10.1145/2020408.2020444","title":"Unbiased online active learning in data streams","display_name":"Unbiased online active learning in data streams","publication_year":2011,"publication_date":"2011-08-21","ids":{"openalex":"https://openalex.org/W2108740451","doi":"https://doi.org/10.1145/2020408.2020444","mag":"2108740451"},"language":"en","primary_location":{"id":"doi:10.1145/2020408.2020444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-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/A5056008057","display_name":"Wei Chu","orcid":"https://orcid.org/0000-0002-0276-224X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Chu","raw_affiliation_strings":["Microsoft, Redmond, USA","Microsoft Redmond, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112356991","display_name":"Martin Zinkevich","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Zinkevich","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, USA",", Yahoo Labs, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":", Yahoo Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107006279","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-1264-8483"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, USA",", Yahoo Labs, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":", Yahoo Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113588167","display_name":"Achint Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Achint Thomas","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, USA",", Yahoo Labs, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":", Yahoo Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112455964","display_name":"Belle L. Tseng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Belle Tseng","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, USA",", Yahoo Labs, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":", Yahoo Labs, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056008057"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":8.3329,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.97506234,"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":"195","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T12761","display_name":"Data Stream Mining Techniques","score":0.9983000159263611,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7707269191741943},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.6449998021125793},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6051139831542969},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.564357340335846},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5268142223358154},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5173910856246948},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49159106612205505},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.491193026304245},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.48323020339012146},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.47610434889793396},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4743807911872864},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4688393175601959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4462571442127228},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43685102462768555},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.42298823595046997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1297372281551361},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.12363061308860779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7707269191741943},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6449998021125793},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6051139831542969},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.564357340335846},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5268142223358154},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5173910856246948},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49159106612205505},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.491193026304245},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.48323020339012146},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.47610434889793396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4743807911872864},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4688393175601959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4462571442127228},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43685102462768555},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.42298823595046997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1297372281551361},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.12363061308860779},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2020408.2020444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.6848","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.6848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/~chuwei/paper/Chu11Unbiased.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W120286951","https://openalex.org/W1484084878","https://openalex.org/W1515272691","https://openalex.org/W1528361845","https://openalex.org/W1553262910","https://openalex.org/W2022637125","https://openalex.org/W2039650962","https://openalex.org/W2080021732","https://openalex.org/W2085989833","https://openalex.org/W2088844710","https://openalex.org/W2108736173","https://openalex.org/W2111145173","https://openalex.org/W2115305054","https://openalex.org/W2137956165","https://openalex.org/W2137959503","https://openalex.org/W2148825261","https://openalex.org/W2151023586","https://openalex.org/W2157958821","https://openalex.org/W2162979096","https://openalex.org/W2167595980","https://openalex.org/W2309755354","https://openalex.org/W2570764145","https://openalex.org/W2622248957","https://openalex.org/W2903158431","https://openalex.org/W2999905431","https://openalex.org/W3014146993","https://openalex.org/W3171280080","https://openalex.org/W6676257183","https://openalex.org/W6991122698"],"related_works":["https://openalex.org/W4307392573","https://openalex.org/W2802243998","https://openalex.org/W2736127210","https://openalex.org/W2329342202","https://openalex.org/W2574092225","https://openalex.org/W4200217704","https://openalex.org/W2161835057","https://openalex.org/W1521014365","https://openalex.org/W3208495060","https://openalex.org/W2740428142"],"abstract_inverted_index":{"Unlabeled":[0],"samples":[1,21],"can":[2],"be":[3],"intelligently":[4],"selected":[5],"for":[6],"labeling":[7,51],"to":[8,30,78,97,125],"minimize":[9,79],"classification":[10,46],"error.":[11],"In":[12,39,100],"many":[13],"real-world":[14],"applications,":[15],"a":[16,24,36,56,105,112],"large":[17],"number":[18],"of":[19,108,144],"unlabeled":[20],"arrive":[22],"in":[23,35,52,69,82,116,149],"streaming":[25],"manner,":[26],"making":[27],"it":[28],"impossible":[29],"maintain":[31],"all":[32],"the":[33,66,70,80,83,142,150],"data":[34,53,106],"candidate":[37],"pool.":[38],"this":[40],"work,":[41],"we":[42,103],"focus":[43],"on":[44,60,111],"binary":[45],"problems":[47],"and":[48,73,120,136],"study":[49],"selective":[50],"streams":[54],"where":[55],"decision":[57],"is":[58],"required":[59],"each":[61],"sample":[62],"sequentially.":[63],"We":[64],"consider":[65],"unbiasedness":[67],"property":[68],"sampling":[71,128],"process,":[72],"design":[74],"optimal":[75],"instrumental":[76],"distributions":[77],"variance":[81],"stochastic":[84],"process.":[85],"Meanwhile,":[86],"Bayesian":[87],"linear":[88],"classifiers":[89],"with":[90,153],"weighted":[91],"maximum":[92],"likelihood":[93],"are":[94],"optimized":[95],"online":[96,145],"estimate":[98],"parameters.":[99],"empirical":[101],"evaluation,":[102],"collect":[104],"stream":[107],"user-generated":[109],"comments":[110],"commercial":[113],"news":[114],"portal":[115],"30":[117],"consecutive":[118],"days,":[119],"carry":[121],"out":[122],"offline":[123],"evaluation":[124],"compare":[126],"various":[127],"strategies,":[129],"including":[130],"unbiased":[131],"active":[132,146],"learning,":[133,147],"biased":[134],"variants,":[135],"random":[137],"sampling.":[138],"Experimental":[139],"results":[140],"verify":[141],"usefulness":[143],"especially":[148],"non-stationary":[151],"situation":[152],"concept":[154],"drift.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}