{"id":"https://openalex.org/W4320024053","doi":"https://doi.org/10.1109/bigdata55660.2022.10021016","title":"FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems","display_name":"FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024053","doi":"https://doi.org/10.1109/bigdata55660.2022.10021016"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10021016","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10021016","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5075541712","display_name":"Weijie Zhao","orcid":"https://orcid.org/0000-0003-0967-1436"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weijie Zhao","raw_affiliation_strings":["Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193"],"affiliations":[{"raw_affiliation_string":"Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006865469","display_name":"Xuewu Jiao","orcid":"https://orcid.org/0009-0004-6530-4774"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewu Jiao","raw_affiliation_strings":["Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193"],"affiliations":[{"raw_affiliation_string":"Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100945726","display_name":"Xinsheng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Luo","raw_affiliation_strings":["Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193"],"affiliations":[{"raw_affiliation_string":"Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080952417","display_name":"Jingxue Li","orcid":"https://orcid.org/0000-0003-2150-6265"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxue Li","raw_affiliation_strings":["Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193"],"affiliations":[{"raw_affiliation_string":"Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015585821","display_name":"Belhal Karimi","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Belhal Karimi","raw_affiliation_strings":["Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193"],"affiliations":[{"raw_affiliation_string":"Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100435468","display_name":"Ping Li","orcid":"https://orcid.org/0000-0001-8272-6582"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193"],"affiliations":[{"raw_affiliation_string":"Baidu Research Baidu Search Ads (Phoenix Nest), Baidu Inc,Cognitive Computing Lab,Beijing,China,100193","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075541712"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":0.291,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57265081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"53","issue":null,"first_page":"2461","last_page":"2466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.998199999332428,"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":0.998199999332428,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8528652191162109},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.697403073310852},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6502820253372192},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6006960272789001},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.542930006980896},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5214740037918091},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4606618285179138},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45158228278160095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43918752670288086},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.43460094928741455},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39730775356292725},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22456738352775574},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13963797688484192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528652191162109},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.697403073310852},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6502820253372192},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6006960272789001},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.542930006980896},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5214740037918091},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4606618285179138},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45158228278160095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43918752670288086},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.43460094928741455},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39730775356292725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22456738352775574},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13963797688484192},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10021016","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10021016","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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":30,"referenced_works":["https://openalex.org/W2070996757","https://openalex.org/W2102221597","https://openalex.org/W2173213060","https://openalex.org/W2512971201","https://openalex.org/W2517540742","https://openalex.org/W2533696134","https://openalex.org/W2548570154","https://openalex.org/W2604662567","https://openalex.org/W2723293840","https://openalex.org/W2793768763","https://openalex.org/W2950960796","https://openalex.org/W2984020950","https://openalex.org/W3034483718","https://openalex.org/W3034709327","https://openalex.org/W3043590771","https://openalex.org/W3093907268","https://openalex.org/W3104030692","https://openalex.org/W3114904768","https://openalex.org/W3122305203","https://openalex.org/W3154197656","https://openalex.org/W3154704661","https://openalex.org/W3174178850","https://openalex.org/W3209943551","https://openalex.org/W4288083766","https://openalex.org/W4293248235","https://openalex.org/W4318147416","https://openalex.org/W6674970736","https://openalex.org/W6683646410","https://openalex.org/W6704404914","https://openalex.org/W6774806506"],"related_works":["https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2105580438","https://openalex.org/W2057435755","https://openalex.org/W2018782216","https://openalex.org/W2949620858","https://openalex.org/W2770877918","https://openalex.org/W1989375655","https://openalex.org/W2911113383"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"been":[3],"widely":[4],"deployed":[5],"for":[6],"online":[7],"ads":[8,145],"systems":[9],"to":[10,20,75,107],"predict":[11],"click-through":[12],"rate":[13],"(CTR).":[14],"Practitioners":[15],"frequently":[16],"re-train":[17],"CTR":[18,28],"models":[19],"test":[21],"their":[22],"new":[23],"extracted":[24],"features.":[25],"As":[26],"the":[27,41,50,66,70,77,81,95,137,150],"model":[29],"training":[30,51,62,71],"relies":[31],"on":[32,72,98,143],"a":[33,46,59,102,114],"large":[34],"number":[35],"of":[36,49,80,152],"raw":[37],"input":[38],"data":[39],"logs,":[40],"feature":[42,67,82,87,140],"extraction":[43,68,88,141],"step":[44],"takes":[45],"significant":[47],"portion":[48],"time.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"FeatureBox,":[58],"novel":[60],"end-to-end":[61],"framework":[63,142],"that":[64,120],"pipelines":[65],"and":[69,93,133],"GPU":[73,91,116,123],"servers":[74],"save":[76],"intermediate":[78],"I/O":[79],"extraction.":[83],"We":[84,100,112,129],"rewrite":[85],"computation-intensive":[86],"operators":[89,92],"as":[90],"leave":[94],"memory-intensive":[96],"operator":[97,104],"CPUs.":[99],"introduce":[101],"layer-wise":[103],"scheduling":[105],"algorithm":[106,119],"schedule":[108],"these":[109],"heterogeneous":[110],"operators.":[111],"present":[113],"light-weight":[115],"memory":[117,124],"management":[118],"supports":[121],"dynamic":[122],"allocation":[125],"with":[126,136],"minimal":[127],"overhead.":[128],"experimentally":[130],"evaluate":[131],"FeatureBox":[132],"compare":[134],"it":[135],"previous":[138],"in-production":[139],"two":[144],"applications.":[146],"The":[147],"results":[148],"confirm":[149],"effectiveness":[151],"our":[153],"proposed":[154],"method.":[155]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}