{"id":"https://openalex.org/W4393180038","doi":"https://doi.org/10.1145/3639306","title":"CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models","display_name":"CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4393180038","doi":"https://doi.org/10.1145/3639306"},"language":"en","primary_location":{"id":"doi:10.1145/3639306","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639306","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-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/A5100462441","display_name":"Hailin Zhang","orcid":"https://orcid.org/0009-0000-4188-7742"},"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":true,"raw_author_name":"Hailin Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101916543","display_name":"Zirui Liu","orcid":"https://orcid.org/0000-0001-9062-6565"},"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":"Zirui Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081335123","display_name":"Boxuan Chen","orcid":"https://orcid.org/0009-0006-3719-2685"},"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":"Boxuan Chen","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048093695","display_name":"Yikai Zhao","orcid":"https://orcid.org/0000-0003-2495-7774"},"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":"Yikai Zhao","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090882844","display_name":"T. P. Zhao","orcid":"https://orcid.org/0009-0005-7201-2152"},"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":"Tong Zhao","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069277955","display_name":"Tong Yang","orcid":"https://orcid.org/0000-0003-2402-5854"},"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":"Tong Yang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","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, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100462441"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":8.9562,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.976537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"28"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9868000149726868,"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/embedding","display_name":"Embedding","score":0.8247264623641968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8164325952529907},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5321575403213501},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5058279037475586},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4914466142654419},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4281185269355774},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4221493601799011},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3610745072364807},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33762675523757935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32924702763557434}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8247264623641968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164325952529907},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5321575403213501},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5058279037475586},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4914466142654419},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4281185269355774},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4221493601799011},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3610745072364807},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33762675523757935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32924702763557434},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639306","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639306","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2070996757","https://openalex.org/W2080234606","https://openalex.org/W2084677224","https://openalex.org/W2158498225","https://openalex.org/W2162332844","https://openalex.org/W2439904216","https://openalex.org/W2475334473","https://openalex.org/W2560674852","https://openalex.org/W2604662567","https://openalex.org/W2723293840","https://openalex.org/W2808923818","https://openalex.org/W2834288129","https://openalex.org/W2963898466","https://openalex.org/W2964182926","https://openalex.org/W2984020950","https://openalex.org/W2996471668","https://openalex.org/W3011493836","https://openalex.org/W3011807731","https://openalex.org/W3016842236","https://openalex.org/W3043433718","https://openalex.org/W3046744391","https://openalex.org/W3080797160","https://openalex.org/W3082891099","https://openalex.org/W3088463703","https://openalex.org/W3117684406","https://openalex.org/W3122089757","https://openalex.org/W3130104841","https://openalex.org/W3154430477","https://openalex.org/W3173839890","https://openalex.org/W3177390287","https://openalex.org/W3186509987","https://openalex.org/W3189127798","https://openalex.org/W3197720002","https://openalex.org/W3197870239","https://openalex.org/W3198024709","https://openalex.org/W3208543775","https://openalex.org/W3210980860","https://openalex.org/W4210690412","https://openalex.org/W4226012237","https://openalex.org/W4226328099","https://openalex.org/W4247950230","https://openalex.org/W4248708867","https://openalex.org/W4282576620","https://openalex.org/W4283326127","https://openalex.org/W4293210201","https://openalex.org/W4294977709","https://openalex.org/W4296591840","https://openalex.org/W4309581333","https://openalex.org/W4311209912","https://openalex.org/W4312968362","https://openalex.org/W4375928354","https://openalex.org/W4380433170","https://openalex.org/W4382239994","https://openalex.org/W4386351750","https://openalex.org/W4386352396","https://openalex.org/W4388535562","https://openalex.org/W4388535592","https://openalex.org/W6600351811"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"Recently,":[0],"the":[1,57,121,152,161,167],"growing":[2],"memory":[3,33,70,81],"demands":[4],"of":[5,63,155,163,201,206],"embedding":[6,23,131,135,148,153,180],"tables":[7,154],"in":[8,106],"Deep":[9],"Learning":[10],"Recommendation":[11],"Models":[12],"(DLRMs)":[13],"pose":[14],"great":[15],"challenges":[16],"for":[17],"model":[18,168],"training":[19],"and":[20,37,50,78,91,102,165,185,194],"deployment.":[21],"Existing":[22],"compression":[24,53,181,199],"solutions":[25],"cannot":[26],"simultaneously":[27],"meet":[28],"three":[29],"key":[30],"design":[31,61,140],"requirements:":[32],"efficiency,":[34],"low":[35],"latency,":[36],"adaptability":[38],"to":[39,66,72,82,98,128,150],"dynamic":[40],"data":[41,94],"distribution.":[42],"This":[43],"paper":[44],"presents":[45],"CAFE,":[46,86],"a":[47,89,117,145,198],"Compact,":[48],"Adaptive,":[49],"Fast":[51],"Embedding":[52],"framework":[54,149],"that":[55,175],"addresses":[56],"above":[58],"requirements.":[59],"The":[60,203],"philosophy":[62],"CAFE":[64,176,207],"is":[65],"dynamically":[67],"allocate":[68,79],"more":[69],"resources":[71],"important":[73],"features":[74,105,127],"(called":[75],"hot":[76,104,112],"features),":[77],"less":[80],"unimportant":[83],"ones.":[84],"In":[85],"we":[87,114,124,142],"propose":[88,144],"fast":[90],"lightweight":[92],"sketch":[93],"structure,":[95],"named":[96],"HotSketch,":[97,164],"capture":[99],"feature":[100],"importance":[101],"report":[103],"real":[107],"time.":[108],"For":[109,120],"each":[110],"reported":[111],"feature,":[113],"assign":[115],"it":[116],"unique":[118],"embedding.":[119],"non-hot":[122,156],"features,":[123],"allow":[125],"multiple":[126],"share":[129],"one":[130],"by":[132,138],"using":[133],"hash":[134,147],"technique.":[136],"Guided":[137],"our":[139],"philosophy,":[141],"further":[143],"multi-level":[146],"optimize":[151],"features.":[157],"We":[158],"theoretically":[159],"analyze":[160,166],"accuracy":[162],"convergence":[169],"against":[170],"deviation.":[171],"Extensive":[172],"experiments":[173],"show":[174],"significantly":[177],"outperforms":[178],"existing":[179],"methods,":[182],"yielding":[183],"3.92%":[184],"3.68%":[186],"superior":[187],"testing":[188],"AUC":[189],"on":[190],"Criteo":[191],"Kaggle":[192],"dataset":[193,196],"CriteoTB":[195],"at":[197,210],"ratio":[200],"10000x.":[202],"source":[204],"codes":[205],"are":[208],"available":[209],"GitHub.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}