{"id":"https://openalex.org/W4205194390","doi":"https://doi.org/10.1109/bigdata52589.2021.9671557","title":"Dynamic Length Factorization Machines for CTR Prediction","display_name":"Dynamic Length Factorization Machines for CTR Prediction","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205194390","doi":"https://doi.org/10.1109/bigdata52589.2021.9671557"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671557","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 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":"2021 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/A5059930466","display_name":"Yohay Kaplan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yohay Kaplan","raw_affiliation_strings":["Yahoo Research, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, Haifa, Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108768449","display_name":"Yair Koren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yair Koren","raw_affiliation_strings":["Yahoo Research, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, Haifa, Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070201473","display_name":"Rina Leibovits","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rina Leibovits","raw_affiliation_strings":["Yahoo Research, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, Haifa, Israel","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010839153","display_name":"Oren Somekh","orcid":"https://orcid.org/0009-0003-8454-5568"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oren Somekh","raw_affiliation_strings":["Yahoo Research, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, Haifa, Israel","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1397,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78697674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9890000224113464,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.8036853075027466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7165985107421875},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6033132076263428},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5162177085876465},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.5054783821105957},{"id":"https://openalex.org/keywords/online-algorithm","display_name":"Online algorithm","score":0.4145898222923279},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3721635341644287},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35131996870040894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3275689482688904}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8036853075027466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7165985107421875},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6033132076263428},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5162177085876465},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.5054783821105957},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.4145898222923279},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3721635341644287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35131996870040894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3275689482688904},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671557","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 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":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1687468423","https://openalex.org/W1788809966","https://openalex.org/W1976517433","https://openalex.org/W1992554260","https://openalex.org/W2005156851","https://openalex.org/W2027913476","https://openalex.org/W2054141820","https://openalex.org/W2061212083","https://openalex.org/W2074694452","https://openalex.org/W2076618162","https://openalex.org/W2146502635","https://openalex.org/W2158698691","https://openalex.org/W2173213060","https://openalex.org/W2295739661","https://openalex.org/W2509235963","https://openalex.org/W2572651649","https://openalex.org/W2605350416","https://openalex.org/W2614013894","https://openalex.org/W2747760596","https://openalex.org/W2788490371","https://openalex.org/W2982896193","https://openalex.org/W2986115522","https://openalex.org/W3033138048","https://openalex.org/W3081362488","https://openalex.org/W3083058384","https://openalex.org/W3098723082","https://openalex.org/W3122305203","https://openalex.org/W3132126111","https://openalex.org/W4226150639","https://openalex.org/W6638443938","https://openalex.org/W6681435938","https://openalex.org/W6774304515","https://openalex.org/W6779547070","https://openalex.org/W6782365421","https://openalex.org/W6791179192"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2194570607"],"abstract_inverted_index":{"Ad":[0],"click-though":[1],"rate":[2],"prediction":[3,32,115],"(pCTR)":[4],"is":[5,23,58,80,130,331],"one":[6],"of":[7,11,18,62,109,137,150,178,201,232,239,250,317],"the":[8,15,54,63,88,100,125,138,148,151,155,176,179,214,224,230,233,237,247,251,256,314],"core":[9],"tasks":[10],"online":[12,119,199],"advertising.":[13],"Driving":[14],"pCTR":[16],"models":[17,40,116,319],"Yahoo":[19],"Gemini":[20,211],"native":[21,212],"advertising":[22],"OFFSET":[24,39,96],"-":[25,287],"a":[26,50,59,133,166,190,206,288,293],"feature":[27,65,183,277],"enhanced":[28],"collaborative-filtering":[29],"based":[30,296],"event":[31],"algorithm.":[33],"Due":[34],"to":[35,146,260,269,273,312,326],"data":[36],"sparsity":[37],"issues":[38],"both":[41,94],"users":[42],"and":[43,97,111,205],"items":[44],"by":[45,83,106,235,253,320],"mapping":[46],"their":[47],"features":[48],"into":[49,218,222],"latent":[51,107,193,241],"space,":[52,242],"where":[53,124],"resulting":[55],"user":[56,64,305],"vector":[57,194,278],"non-linear":[60],"function":[61],"vectors":[66,108,180],"(e.g.,":[67],"age,":[68],"gender,":[69],"hour,":[70],"etc.)":[71],"which":[72],"allows":[73],"pairwise":[74,77,102,139,276],"dependencies.":[75],"This":[76],"dependencies":[78],"concept":[79],"also":[81,245,281],"used":[82,118],"other":[84],"algorithms":[85],"such":[86],"as":[87],"Field-aware":[89],"Factorization":[90,169],"Machines":[91,170],"(FFM).":[92],"However,":[93],"in":[95,98,144],"FFM,":[99],"different":[101],"interactions":[103,140],"are":[104,117],"modeled":[105],"constant":[110],"equal":[112],"lengths.":[113,279],"When":[114],"for":[120,181,291],"serving":[121,127,210],"real":[122],"traffic,":[123,213],"total":[126,248],"model":[128,152,234,252,295,300,329],"size":[129,249],"often":[131],"limited,":[132],"non":[134],"uniform":[135],"representation":[136],"should":[141],"be":[142,267],"considered":[143],"order":[145],"maximize":[147],"accuracy":[149,231],"while":[153,187],"consuming":[154],"same":[156],"or":[157],"even":[158],"less":[159],"space.":[160],"In":[161],"this":[162,308],"work":[163],"we":[164,262,310],"present":[165,282],"Dynamic":[167],"Length":[168],"(DLFM)":[171],"algorithm":[172,257,272],"that":[173,264,301,330],"dynamically":[174],"optimizes":[175],"length":[177,238],"each":[182,240],"interaction":[184],"during":[185],"training,":[186],"not":[188,227],"exceeding":[189],"maximal":[191],"overall":[192],"size.":[195],"After":[196],"showing":[197],"good":[198],"performance":[200],"1.46%":[202],"revenue":[203],"lift":[204],"2.15%":[207],"CTR":[208],"lift,":[209],"DLFM":[215,225,265],"was":[216,258],"pushed":[217],"production.":[219],"Since":[220],"integrated":[221],"production,":[223],"has":[226,244,302],"only":[228],"improved":[229],"optimizing":[236],"but":[243],"reduced":[246],"25%.":[254],"Although":[255],"applied":[259,268],"OFFSET,":[261],"show":[263],"can":[266],"any":[270],"FFM-like":[271],"optimize":[274],"its":[275],"We":[280],"an":[283,298,327],"Educated":[284],"Model":[285],"Initialization":[286],"novel":[289],"mechanism":[290],"initializing":[292],"new":[294],"on":[297],"existing":[299],"some":[303],"mutual":[304],"features.":[306],"Using":[307],"mechanism,":[309],"managed":[311],"reduce":[313],"training":[315],"time":[316],"our":[318],"more":[321],"than":[322],"90%":[323],"when":[324],"compared":[325],"equivalent":[328],"trained":[332],"from":[333],"\"scratch\".":[334]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}