{"id":"https://openalex.org/W2751219672","doi":"https://doi.org/10.14778/3137628.3137649","title":"LDA*","display_name":"LDA*","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2751219672","doi":"https://doi.org/10.14778/3137628.3137649","mag":"2751219672"},"language":"en","primary_location":{"id":"doi:10.14778/3137628.3137649","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137649","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/249800","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048392313","display_name":"Lele Yut","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lele Yut","raw_affiliation_strings":["Peking University and Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and Tencent Inc","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383731","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0002-8105-7505"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014615052","display_name":"Yingxia Shao","orcid":"https://orcid.org/0000-0002-8559-2628"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingxia Shao","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cui","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7673,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95717217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":"11","first_page":"1406","last_page":"1417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9923999905586243,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9915000200271606,"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/computer-science","display_name":"Computer science","score":0.8363698124885559},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6083313822746277},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5352460145950317},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5281457901000977},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.521395742893219},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4815538227558136},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4486992061138153},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44700363278388977},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4424344003200531},{"id":"https://openalex.org/keywords/virtualization","display_name":"Virtualization","score":0.4169466495513916},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4103468656539917},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3763500154018402},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17235460877418518},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14308476448059082},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12570521235466003},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12261581420898438},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.1150883138179779},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1078137457370758}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363698124885559},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6083313822746277},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5352460145950317},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5281457901000977},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.521395742893219},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4815538227558136},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4486992061138153},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44700363278388977},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4424344003200531},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.4169466495513916},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4103468656539917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3763500154018402},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17235460877418518},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14308476448059082},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12570521235466003},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12261581420898438},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.1150883138179779},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1078137457370758},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/3137628.3137649","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137649","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/249800","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/249800","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the VLDB Endowment, 10 (11)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.3929/ethz-b-000224606","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000224606","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/249800","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/249800","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the VLDB Endowment, 10 (11)","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2588877265","display_name":"Flexible Optical Cross-connect Nodes enabling next generation flexible optical networking","funder_award_id":"318415","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1600293573","https://openalex.org/W1609010894","https://openalex.org/W1650067024","https://openalex.org/W1980617223","https://openalex.org/W2001082470","https://openalex.org/W2001975024","https://openalex.org/W2041517243","https://openalex.org/W2052261215","https://openalex.org/W2065221212","https://openalex.org/W2083842231","https://openalex.org/W2087937280","https://openalex.org/W2110529144","https://openalex.org/W2118034653","https://openalex.org/W2130428211","https://openalex.org/W2132737349","https://openalex.org/W2133568543","https://openalex.org/W2146341620","https://openalex.org/W2150731624","https://openalex.org/W2153029569","https://openalex.org/W2153579005","https://openalex.org/W2159080219","https://openalex.org/W2161353674","https://openalex.org/W2166851633","https://openalex.org/W2338322935","https://openalex.org/W2579247884","https://openalex.org/W2589642470","https://openalex.org/W2604272474","https://openalex.org/W2612026221","https://openalex.org/W2950133940","https://openalex.org/W2963491860","https://openalex.org/W4285719527","https://openalex.org/W6679607006","https://openalex.org/W6683847445","https://openalex.org/W6733965320"],"related_works":["https://openalex.org/W4290802965","https://openalex.org/W97789383","https://openalex.org/W3087516072","https://openalex.org/W2727156679","https://openalex.org/W4289406402","https://openalex.org/W2364071303","https://openalex.org/W1483053255","https://openalex.org/W2896097814","https://openalex.org/W20221657","https://openalex.org/W2321648686"],"abstract_inverted_index":{"We":[0,113,177],"present":[1],"LDA*,":[2],"a":[3,78,100,115,146,163,201,235,263],"system":[4,117,268],"that":[5,59,85,149,213],"has":[6,124,280],"been":[7,282],"deployed":[8],"in":[9,33,51,81,183],"one":[10],"of":[11,20,30,61,71,103,156,166,186,229],"the":[12,57,62,82,170,218,227,230,249],"largest":[13],"Internet":[14],"companies":[15],"to":[16,45,92,175,193,199,217,255,271,277,284],"fulfil":[17],"their":[18,37],"requirements":[19],"\"topic":[21],"modeling":[22,65,287],"as":[23,41,43],"an":[24,208],"internal":[25],"service\"":[26],"---relying":[27],"on":[28,134,140,180],"thousands":[29,185],"machines,":[31],"engineers":[32],"different":[34,125,137,151,154,190],"sectors":[35],"submit":[36],"data,":[38],"some":[39,215],"are":[40],"large":[42],"1.8TB,":[44],"LDA*":[46,53],"and":[47,111,128,168,195,234,242,279],"get":[48],"results":[49],"back":[50],"hours.":[52],"is":[54,67,75,99,207,224,269],"motivated":[55,225],"by":[56,90,132,173,226,253,275],"observation":[58],"none":[60],"existing":[63,73,273],"topic":[64,202,286],"systems":[66,74,274],"robust":[68],"enough":[69],"---Each":[70],"these":[72,120,258],"designed":[76],"for":[77,153,289],"specific":[79],"point":[80],"tradeoff":[83,118,237],"space":[84],"can":[86],"be":[87],"sub-optimal,":[88],"sometimes":[89,131],"up":[91,174,254,276],"10\u00d7,":[93],"across":[94,162],"workloads.":[95],"Our":[96,204],"first":[97],"contribution":[98,206],"systematic":[101],"study":[102],"all":[104],"recently":[105],"proposed":[106],"samplers:":[107],"AliasLDA,":[108],"F+LDA,":[109],"LightLDA,":[110],"WarpLDA.":[112],"discovered":[114,239],"novel":[116,236],"among":[119],"samplers.":[121],"Each":[122],"sampler":[123,148,172],"sampling":[126],"complexity":[127],"performs":[129],"differently,":[130],"5\u00d7,":[133],"documents":[135],"with":[136,189,262],"lengths.":[138],"Based":[139],"this":[141,245],"tradeoff,":[142],"we":[143,238,247],"further":[144],"developed":[145],"hybrid":[147,159],"uses":[150],"samplers":[152],"types":[155],"documents.":[157],"This":[158,222],"approach":[160],"works":[161],"wide":[164],"range":[165],"workloads":[167],"outperforms":[169],"fastest":[171],"2x.":[176],"then":[178],"focused":[179],"distributed":[181],"environments":[182],"which":[184],"workers,":[187],"each":[188],"performance":[191],"(due":[192],"virtualization":[194],"resource":[196],"sharing),":[197],"coordinate":[198],"train":[200],"model.":[203],"second":[205],"asymmetric":[209],"parameter":[210,219],"server":[211,220],"architecture":[212,223,252],"pushes":[214],"computation":[216],"side.":[221],"skew":[228],"word":[231],"frequency":[232],"distribution":[233],"between":[240],"communication":[241],"computation.":[243],"With":[244,257],"architecture,":[246],"outperform":[248,272],"traditional,":[250],"symmetric":[251],"2\u00d7.":[256],"two":[259],"contributions,":[260],"together":[261],"carefully":[264],"engineered":[265],"implementation,":[266],"our":[267],"able":[270],"10\u00d7":[278],"already":[281],"running":[283],"provide":[285],"services":[288],"more":[290],"than":[291],"six":[292],"months.":[293]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2017-09-15T00:00:00"}
