{"id":"https://openalex.org/W4224323430","doi":"https://doi.org/10.1145/3485447.3511973","title":"Enterprise-Scale Search: Accelerating Inference for Sparse Extreme Multi-Label Ranking Trees","display_name":"Enterprise-Scale Search: Accelerating Inference for Sparse Extreme Multi-Label Ranking Trees","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4224323430","doi":"https://doi.org/10.1145/3485447.3511973"},"language":"en","primary_location":{"id":"doi:10.1145/3485447.3511973","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3511973","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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":"Proceedings of the ACM Web Conference 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049265592","display_name":"Philip A. Etter","orcid":"https://orcid.org/0000-0002-6657-8230"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip A. Etter","raw_affiliation_strings":["Institute for Computational and Mathematical Engineering, Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computational and Mathematical Engineering, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017721496","display_name":"Kai Zhong","orcid":"https://orcid.org/0000-0002-9993-6954"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhong","raw_affiliation_strings":["Amazon Search, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Search, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023183059","display_name":"Hsiang\u2010Fu Yu","orcid":"https://orcid.org/0000-0001-5235-2962"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsiang-Fu Yu","raw_affiliation_strings":["Amazon Search, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Search, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011918131","display_name":"Lexing Ying","orcid":"https://orcid.org/0000-0003-1547-1457"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lexing Ying","raw_affiliation_strings":["Institute for Computational and Mathematical Engineering, Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computational and Mathematical Engineering, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Inderjit Dhillon","raw_affiliation_strings":["Amazon Search, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Search, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7461501359939575},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6133618354797363},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5951704382896423},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36185353994369507},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3405560851097107},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3242945373058319},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32218122482299805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29664650559425354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461501359939575},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6133618354797363},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5951704382896423},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36185353994369507},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3405560851097107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3242945373058319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32218122482299805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29664650559425354},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3485447.3511973","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3511973","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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":"Proceedings of the ACM Web Conference 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1520511539","https://openalex.org/W1878054055","https://openalex.org/W1893178273","https://openalex.org/W1990832096","https://openalex.org/W2130289795","https://openalex.org/W2542072367","https://openalex.org/W2788125153","https://openalex.org/W3172352177"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W4321636575","https://openalex.org/W2741131631","https://openalex.org/W2045526782","https://openalex.org/W2156919374","https://openalex.org/W1483472507","https://openalex.org/W1984019423","https://openalex.org/W4280588203"],"abstract_inverted_index":{"Tree-based":[0],"models":[1,21,41,46,73,175],"underpin":[2],"many":[3,172],"modern":[4],"semantic":[5,191],"search":[6,193],"engines":[7],"and":[8,109,138,162,167,170,176,199,285],"recommender":[9],"systems":[10],"due":[11],"to":[12,99,105,115,132,188,229,255],"their":[13,264],"sub-linear":[14],"inference":[15,119,136,164,220,265],"times.":[16],"In":[17],"industrial":[18,183],"applications,":[19,184],"these":[20],"operate":[22],"at":[23,35,121,267,276,289],"extreme":[24,36,75,146],"scales,":[25],"where":[26],"every":[27],"bit":[28],"of":[29,129,203,252,260],"performance":[30,113],"is":[31,103,273],"critical.":[32],"Memory":[33],"constraints":[34],"scales":[37],"also":[38],"require":[39],"that":[40,152,247],"be":[42],"sparse,":[43],"hence":[44],"tree-based":[45,72],"are":[47,57],"often":[48],"back-ended":[49],"by":[50],"sparse":[51,60,88,94,135,241],"matrix":[52,61,95,242],"algebra":[53],"routines.":[54],"However,":[55],"there":[56],"currently":[58],"no":[59,122,227],"techniques":[62],"specifically":[63,97],"designed":[64],"for":[65,74,287],"the":[66,86,160,236],"sparsity":[67],"structure":[68],"one":[69],"encounters":[70],"in":[71,182,216,263],"multi-label":[76,147],"ranking/classification":[77],"(XMR/XMC)":[78],"problems.":[79],"To":[80,178],"address":[81],"this":[82],"issue,":[83],"we":[84,185,245],"present":[85],"masked":[87],"chunk":[89],"multiplication":[90],"(MSCM)":[91],"technique,":[92],"a":[93,111,126,143,209,257],"technique":[96,224],"tailored":[98],"XMR":[100,253],"trees.":[101],"MSCM":[102,130,153,187,223,248],"easy":[104],"implement,":[106],"embarrassingly":[107],"parallelizable,":[108],"offers":[110],"significant":[112],"boost":[114],"any":[116],"existing":[117],"tree":[118,174],"pipeline":[120],"cost.":[123,270],"We":[124,150],"perform":[125],"comprehensive":[127],"study":[128],"applied":[131],"several":[133],"different":[134,173],"schemes":[137],"benchmark":[139],"our":[140,282],"methods":[141],"on":[142,171,208],"general":[144],"purpose":[145],"ranking":[148],"framework.":[149],"observe":[151],"gives":[154,234],"consistently":[155],"dramatic":[156],"speedups":[157],"across":[158],"both":[159],"online":[161],"batch":[163],"settings,":[165,169],"single-":[166],"multi-threaded":[168],"datasets.":[177],"demonstrate":[179],"its":[180],"utility":[181],"apply":[186],"an":[189,213],"enterprise-scale":[190],"product":[192],"problem":[194],"with":[195],"100":[196],"million":[197],"products":[198],"achieve":[200],"sub-millisecond":[201],"latency":[202,217],"0.88":[204],"ms":[205],"per":[206],"query":[207],"single":[210],"thread":[211],"\u2014":[212],"8x":[214],"reduction":[215],"over":[218],"vanilla":[219],"techniques.":[221,243],"The":[222],"requires":[225],"absolutely":[226],"sacrifices":[228],"model":[230],"accuracy":[231],"as":[232,239,279,281],"it":[233],"exactly":[235],"same":[237],"results":[238],"standard":[240],"Therefore,":[244],"believe":[246],"will":[249],"enable":[250],"users":[251],"trees":[254],"save":[256],"substantial":[258],"amount":[259],"compute":[261],"resources":[262],"pipelines":[266],"very":[268],"little":[269],"Our":[271],"code":[272,286],"publicly":[274],"available":[275],"https://github.com/amzn/pecos":[277],",":[278],"well":[280],"complete":[283],"benchmarks":[284],"reproduction":[288],"https://github.com/UniqueUpToPermutation/pecos/tree/benchmark.":[290]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}