{"id":"https://openalex.org/W2665024313","doi":"https://doi.org/10.1145/3077136.3084135","title":"Computing Web-scale Topic Models using an Asynchronous Parameter Server","display_name":"Computing Web-scale Topic Models using an Asynchronous Parameter Server","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2665024313","doi":"https://doi.org/10.1145/3077136.3084135","mag":"2665024313"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3084135","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3084135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1605.07422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042795557","display_name":"Rolf Jagerman","orcid":"https://orcid.org/0000-0002-5169-495X"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rolf Jagerman","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014921416","display_name":"Carsten Eickhoff","orcid":"https://orcid.org/0000-0001-9895-4061"},"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":"Carsten Eickhoff","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1337","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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":0.9979000091552734,"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/T11719","display_name":"Data Quality and Management","score":0.9969000220298767,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8758605122566223},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6541783809661865},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6207837462425232},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.597941517829895},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5705839395523071},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.45097818970680237},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39473310112953186},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3757246136665344},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.25399112701416016},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.15253859758377075},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12276196479797363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8758605122566223},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6541783809661865},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6207837462425232},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.597941517829895},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5705839395523071},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.45097818970680237},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39473310112953186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3757246136665344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25399112701416016},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.15253859758377075},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12276196479797363},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3077136.3084135","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3084135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1605.07422","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.07422","pdf_url":"https://arxiv.org/pdf/1605.07422","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:dare.uva.nl:openaire_cris_publications/bd0c1538-2cbc-4474-8ee5-286a274d1b4e","is_oa":false,"landing_page_url":"https://hdl.handle.net/11245.1/bd0c1538-2cbc-4474-8ee5-286a274d1b4e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/bd0c1538-2cbc-4474-8ee5-286a274d1b4e","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/computing-webscale-topic-models-using-an-asynchronous-parameter-server(bd0c1538-2cbc-4474-8ee5-286a274d1b4e).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/bd0c1538-2cbc-4474-8ee5-286a274d1b4e","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/computing-webscale-topic-models-using-an-asynchronous-parameter-server(bd0c1538-2cbc-4474-8ee5-286a274d1b4e).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR'17 : proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval: August 7-11, 2017, Shinjuku, Tokyo, Japan, 1337 - 1340","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1605.07422","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.07422","pdf_url":"https://arxiv.org/pdf/1605.07422","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1609010894","https://openalex.org/W1650067024","https://openalex.org/W1880262756","https://openalex.org/W2060393849","https://openalex.org/W2107743791","https://openalex.org/W2111946621","https://openalex.org/W2131975293","https://openalex.org/W2161353674","https://openalex.org/W2165599843","https://openalex.org/W2168231600","https://openalex.org/W2304411646","https://openalex.org/W2962844195","https://openalex.org/W4231510805","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4389543811"],"abstract_inverted_index":{"Topic":[0],"models":[1,36],"such":[2,80],"as":[3,81,108],"Latent":[4],"Dirichlet":[5],"Allocation":[6],"(LDA)":[7],"have":[8],"been":[9],"widely":[10],"used":[11,141],"in":[12,113,142],"information":[13],"retrieval":[14],"for":[15,25,33,105],"tasks":[16],"ranging":[17],"from":[18,115],"smoothing":[19],"and":[20,28,60,101,156,172],"feedback":[21],"methods":[22,32],"to":[23,41,62,117,123,129,150,168],"tools":[24],"exploratory":[26],"search":[27],"discovery.":[29],"However,":[30],"classical":[31],"inferring":[34],"topic":[35,74,134],"do":[37],"not":[38,122],"scale":[39],"up":[40,167],"the":[42,103,151],"massive":[43],"size":[44],"of":[45,90,96],"today's":[46,143],"publicly":[47],"available":[48],"Web-scale":[49],"data":[50,98,109,144,171],"sets.":[51],"The":[52],"state-of-the-art":[53,73],"approaches":[54],"rely":[55],"on":[56,162],"custom":[57],"strategies,":[58],"implementations":[59,155],"hardware":[61],"facilitate":[63],"their":[64],"asynchronous,":[65],"communication-intensive":[66],"workloads.":[67],"We":[68,147],"present":[69],"APS-LDA,":[70],"which":[71],"integrates":[72],"modeling":[75,135],"with":[76],"cluster":[77],"computing":[78],"frameworks":[79],"Spark":[82,153],"using":[83],"a":[84,131,163],"novel":[85],"asynchronous":[86],"parameter":[87],"server.":[88],"Advantages":[89],"this":[91],"integration":[92],"include":[93],"convenient":[94],"usage":[95],"existing":[97,152],"processing":[99,145],"pipelines":[100],"eliminating":[102],"need":[104],"disk":[106],"writes":[107],"can":[110,138],"be":[111,140],"kept":[112],"memory":[114],"start":[116],"finish.":[118],"Our":[119],"goal":[120],"is":[121],"outperform":[124],"highly":[125],"customized":[126],"implementations,":[127],"but":[128],"propose":[130],"general":[132],"high-performance":[133],"framework":[136],"that":[137,158],"easily":[139],"pipelines.":[146],"compare":[148],"APS-LDA":[149],"LDA":[154],"show":[157],"our":[159],"system":[160],"can,":[161],"480-core":[164],"cluster,":[165],"process":[166],"135\u00d7":[169],"more":[170,174],"10\u00d7":[173],"topics":[175],"without":[176],"sacricing":[177],"model":[178],"quality.":[179]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2020-11-23T00:00:00"}
