{"id":"https://openalex.org/W2008741686","doi":"https://doi.org/10.1145/2556195.2556242","title":"Sampling dilemma","display_name":"Sampling dilemma","publication_year":2014,"publication_date":"2014-02-18","ids":{"openalex":"https://openalex.org/W2008741686","doi":"https://doi.org/10.1145/2556195.2556242","mag":"2008741686"},"language":"en","primary_location":{"id":"doi:10.1145/2556195.2556242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search 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/A5101844109","display_name":"Jun Feng","orcid":"https://orcid.org/0000-0002-2627-5403"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Feng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021438219","display_name":"Jiang Bian","orcid":"https://orcid.org/0000-0001-6997-1989"},"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"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jiang Bian","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074676968","display_name":"Taifeng Wang","orcid":"https://orcid.org/0009-0007-1116-0228"},"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"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Taifeng Wang","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039536701","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-6225-2110"},"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"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671241","display_name":"Xiaoyan Zhu","orcid":"https://orcid.org/0000-0002-1574-8762"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"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":["CN","US"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101844109"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.4058,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67995111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9968000054359436,"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/T12288","display_name":"Optimization and Search Problems","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.7692182064056396},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.7598072290420532},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7328025102615356},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.623878002166748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5184800028800964},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5019047260284424},{"id":"https://openalex.org/keywords/sampling-distribution","display_name":"Sampling distribution","score":0.4779232144355774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45107290148735046},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4140043258666992},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1942777931690216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13647639751434326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692182064056396},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.7598072290420532},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7328025102615356},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.623878002166748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5184800028800964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5019047260284424},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.4779232144355774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45107290148735046},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4140043258666992},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1942777931690216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13647639751434326},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2556195.2556242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1590012787","https://openalex.org/W1975392791","https://openalex.org/W2053323136","https://openalex.org/W2056705371","https://openalex.org/W2064987260","https://openalex.org/W2069002575","https://openalex.org/W2090883204","https://openalex.org/W2096175520","https://openalex.org/W2107635568","https://openalex.org/W2111748568","https://openalex.org/W2133866996","https://openalex.org/W2139891288","https://openalex.org/W2146422856","https://openalex.org/W2153253904","https://openalex.org/W2162979096","https://openalex.org/W2167547465","https://openalex.org/W2181470043","https://openalex.org/W2338406834","https://openalex.org/W4231741839","https://openalex.org/W4298856664"],"related_works":["https://openalex.org/W2350209916","https://openalex.org/W2475524763","https://openalex.org/W2363851383","https://openalex.org/W2354517252","https://openalex.org/W2387460998","https://openalex.org/W129898351","https://openalex.org/W4383227007","https://openalex.org/W4245258405","https://openalex.org/W2068369387","https://openalex.org/W3128679398"],"abstract_inverted_index":{"Precise":[0],"prediction":[1],"of":[2,56,64,119,172,204],"the":[3,61,75,80,86,95,100,110,117,158,193,196,216,233,242,254],"probability":[4],"that":[5,74,94,157,225],"users":[6],"click":[7,29,65,261],"on":[8,215],"ads":[9],"plays":[10],"a":[11,23,126,141,151,184,220],"key":[12],"role":[13],"in":[14,54,121,174,191,202,260],"sponsored":[15,18,122],"search.":[16],"State-of-the-art":[17],"search":[19,222],"systems":[20],"typically":[21],"employ":[22],"machine":[24],"learning":[25,62],"approach":[26],"to":[27,35,72,92,116,129,144,167],"conduct":[28],"prediction.":[30,262],"While":[31],"paying":[32],"much":[33,257],"attention":[34],"extracting":[36],"useful":[37],"features":[38],"and":[39,199,208],"building":[40],"effective":[41,166],"models,":[42],"previous":[43],"studies":[44],"have":[45],"overshadowed":[46],"seemingly":[47],"less":[48],"obvious":[49],"but":[50,90],"essentially":[51],"important":[52],"challenges":[53,133],"terms":[55,203],"data":[57,78,98,153,198,244],"sampling.":[58],"To":[59,178],"fulfill":[60],"objective":[63],"prediction,":[66],"it":[67,124],"is":[68,125],"not":[69,164],"only":[70],"necessary":[71],"ensure":[73],"sampled":[76,96,197],"training":[77,97,243],"implies":[79],"similar":[81],"input":[82,206],"distribution":[83,207],"compared":[84],"with":[85,109,256],"real":[87,111,200],"world":[88,112,201],"one,":[89],"also":[91],"guarantee":[93],"yield":[99],"consistent":[101],"conditional":[102,209],"output":[103,210],"distribution,":[104],"i.e.":[105],"click-through":[106,217],"rate":[107],"(CTR),":[108],"data.":[113],"However,":[114],"due":[115],"sparseness":[118],"clicks":[120],"search,":[123],"bit":[127],"contradictory":[128],"address":[130,179,232],"these":[131,169],"two":[132,170],"simultaneously.":[134,177],"In":[135],"this":[136,146,180,226],"paper,":[137],"we":[138,182,251],"first":[139],"take":[140],"theoretical":[142],"analysis":[143,154],"reveal":[145],"sampling":[147,161,175,186,228,234,249],"dilemma,":[148],"followed":[149],"by":[150,240,246],"thorough":[152],"which":[155,188],"demonstrates":[156],"straightforward":[159],"random":[160],"method":[162],"may":[163],"be":[165],"balance":[168],"kinds":[171],"consistency":[173,194],"dilemma":[176],"problem,":[181],"propose":[183],"new":[185,227,248],"algorithm":[187,229],"can":[189,230,252],"succeed":[190],"retaining":[192],"between":[195],"both":[205],"distribution.":[211],"Large":[212],"scale":[213],"evaluations":[214],"logs":[218],"from":[219],"commercial":[221],"engine":[223],"demonstrate":[224],"effectively":[231],"dilemma.":[235],"Further":[236],"experiments":[237],"illustrate":[238],"that,":[239],"using":[241],"obtained":[245],"our":[247],"algorithm,":[250],"learn":[253],"model":[255],"higher":[258],"accuracy":[259]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}