{"id":"https://openalex.org/W3172506454","doi":"https://doi.org/10.1145/3447548.3467076","title":"Bootstrapping for Batch Active Sampling","display_name":"Bootstrapping for Batch Active Sampling","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3172506454","doi":"https://doi.org/10.1145/3447548.3467076","mag":"3172506454"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467076","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467076","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067496870","display_name":"Heinrich Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Heinrich Jiang","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111921762","display_name":"Maya R. Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maya R. Gupta","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067496870"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77795395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3086","last_page":"3096"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9950000047683716,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9947999715805054,"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/margin","display_name":"Margin (machine learning)","score":0.7717363238334656},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7074267864227295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6471800208091736},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6240919828414917},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5355880856513977},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5333518981933594},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.4830194413661957},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47109681367874146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42047780752182007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41004621982574463},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3874438405036926},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21314340829849243},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.12356281280517578}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7717363238334656},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7074267864227295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471800208091736},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6240919828414917},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5355880856513977},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5333518981933594},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.4830194413661957},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47109681367874146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42047780752182007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41004621982574463},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3874438405036926},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21314340829849243},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.12356281280517578},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3467076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467076","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"}],"best_oa_location":{"id":"doi:10.1145/3447548.3467076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467076","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3172506454.pdf","grobid_xml":"https://content.openalex.org/works/W3172506454.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W123226248","https://openalex.org/W1549658602","https://openalex.org/W1553262910","https://openalex.org/W1580375566","https://openalex.org/W1590983731","https://openalex.org/W1845402413","https://openalex.org/W1912128066","https://openalex.org/W1978633512","https://openalex.org/W1988747891","https://openalex.org/W1991234467","https://openalex.org/W1993202648","https://openalex.org/W1995945562","https://openalex.org/W2006484294","https://openalex.org/W2016405781","https://openalex.org/W2018770010","https://openalex.org/W2021732807","https://openalex.org/W2025566624","https://openalex.org/W2036150674","https://openalex.org/W2065010255","https://openalex.org/W2080021732","https://openalex.org/W2096623936","https://openalex.org/W2099550922","https://openalex.org/W2101234009","https://openalex.org/W2101927381","https://openalex.org/W2104848109","https://openalex.org/W2107131609","https://openalex.org/W2133288557","https://openalex.org/W2137795521","https://openalex.org/W2139238311","https://openalex.org/W2139573966","https://openalex.org/W2408920689","https://openalex.org/W2551857043","https://openalex.org/W2774918944","https://openalex.org/W2789942211","https://openalex.org/W2963902936","https://openalex.org/W2997591727","https://openalex.org/W3106889297","https://openalex.org/W3141335229","https://openalex.org/W4241850027","https://openalex.org/W6657236616","https://openalex.org/W6680113041","https://openalex.org/W6760443549"],"related_works":["https://openalex.org/W4304699798","https://openalex.org/W4322743207","https://openalex.org/W4223514174","https://openalex.org/W2951109249","https://openalex.org/W3158316258","https://openalex.org/W3082009436","https://openalex.org/W3129868498","https://openalex.org/W2295628041","https://openalex.org/W2597787948","https://openalex.org/W3172506454"],"abstract_inverted_index":{"The":[0,46],"goal":[1],"of":[2,15,27,87,105,177],"active":[3,39,62,131,160,182],"learning":[4],"is":[5],"to":[6,17,19,55,102],"select":[7],"the":[8,25,60,91,126,139,149,156,170],"best":[9],"examples":[10],"from":[11,125],"an":[12],"unlabeled":[13],"pool":[14],"data":[16],"label":[18],"improve":[20],"a":[21,33,84,103,116],"model":[22],"trained":[23],"with":[24],"addition":[26],"these":[28],"labeled":[29],"examples.":[30],"We":[31,82],"discuss":[32],"real-world":[34,166],"use":[35],"case":[36,167],"for":[37,59,66,90,130],"batch":[38,92,150,181],"sampling":[40,63,76,89,142,161],"that":[41,74,94,138],"works":[42,144],"at":[43],"larger":[44,67],"scales.":[45],"standard":[47],"margin":[48,75,88,101,147],"algorithm":[49],"has":[50],"repeatedly":[51],"been":[52],"shown":[53],"difficult":[54],"beat":[56],"in":[57,115],"practice":[58],"classic":[61],"set-up,":[64],"but":[65],"batches":[68],"and":[69,108,118,121,153,173,179],"candidate":[70,96],"pools,":[71],"we":[72,163],"show":[73,137],"may":[77],"not":[78],"provide":[79],"enough":[80],"diversity.":[81],"present":[83],"simple":[85],"variant":[86],"setting":[93],"scores":[95],"samples":[97],"by":[98],"their":[99],"minimum":[100],"set":[104],"bootstrapped":[106],"margins,":[107],"explain":[109],"how":[110],"this":[111],"proposal":[112],"increases":[113],"diversity":[114],"supervised":[117],"efficient":[119],"way,":[120],"why":[122],"it":[123],"differs":[124],"usual":[127],"ensemble":[128],"methods":[129,162],"sampling.":[132,183],"Experiments":[133],"on":[134],"benchmark":[135],"datasets":[136],"proposed":[140],"min-margin":[141],"consistently":[143],"better":[145,154],"than":[146,155],"as":[148],"size":[151],"grows,":[152],"five":[157],"other":[158],"diversity-encouraging":[159],"tested.":[164],"Two":[165],"studies":[168],"illustrate":[169],"practical":[171],"value,":[172],"help":[174],"highlight":[175],"challenges":[176],"applying":[178],"deploying":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}