{"id":"https://openalex.org/W3199460483","doi":"https://doi.org/10.1145/3460231.3474605","title":"Scaling TensorFlow to 300 million predictions per second","display_name":"Scaling TensorFlow to 300 million predictions per second","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3199460483","doi":"https://doi.org/10.1145/3460231.3474605","mag":"3199460483"},"language":"en","primary_location":{"id":"doi:10.1145/3460231.3474605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3474605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","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/2109.09541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jan Hartman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Hartman","raw_affiliation_strings":["Zemanta, an Outbrain company, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zemanta, an Outbrain company, Slovenia","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Davorin Kopi\u010d","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davorin Kopi\u010d","raw_affiliation_strings":["Zemanta, an Outbrain company, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zemanta, an Outbrain company, Slovenia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5115,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62028364,"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":"595","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9955999851226807,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/scaling","display_name":"Scaling","score":0.6315000057220459},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5921000242233276},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5454999804496765},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5424000024795532},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38440001010894775}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6287999749183655},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26969999074935913}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3460231.3474605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3474605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.09541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.09541","pdf_url":"https://arxiv.org/pdf/2109.09541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.09541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.09541","pdf_url":"https://arxiv.org/pdf/2109.09541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2074694452","https://openalex.org/W2076618162","https://openalex.org/W2295739661","https://openalex.org/W2530299800"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,10,27,41],"process":[3],"of":[4],"transitioning":[5],"machine":[6],"learning":[7],"models":[8,42],"to":[9],"TensorFlow":[11],"framework":[12],"at":[13],"a":[14],"large":[15],"scale":[16],"in":[17,43],"an":[18],"online":[19],"advertising":[20],"ecosystem.":[21],"In":[22],"this":[23],"talk":[24],"we":[25,30,35],"address":[26],"key":[28],"challenges":[29],"faced":[31],"and":[32,45],"describe":[33],"how":[34],"successfully":[36],"tackled":[37],"them;":[38],"notably,":[39],"implementing":[40],"TF":[44],"serving":[46],"them":[47],"efficiently":[48],"with":[49],"low":[50],"latency":[51],"using":[52],"various":[53],"optimization":[54],"techniques.":[55]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2021-09-27T00:00:00"}