{"id":"https://openalex.org/W3153940464","doi":"https://doi.org/10.1145/3404835.3463032","title":"Cross-Batch Negative Sampling for Training Two-Tower Recommenders","display_name":"Cross-Batch Negative Sampling for Training Two-Tower Recommenders","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3153940464","doi":"https://doi.org/10.1145/3404835.3463032","mag":"3153940464"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5100376310","display_name":"Jinpeng Wang","orcid":"https://orcid.org/0000-0001-6127-9146"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinpeng Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669373","display_name":"Jieming Zhu","orcid":"https://orcid.org/0000-0002-5666-8320"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083350101","display_name":"Xiuqiang He","orcid":"https://orcid.org/0000-0002-4115-8205"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuqiang He","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1632","last_page":"1636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9979000091552734,"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/T12676","display_name":"Machine Learning and ELM","score":0.9951000213623047,"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":0.7599368095397949},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6405697464942932},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6171541810035706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5199655294418335},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5123980641365051},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5014493465423584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4914897680282593},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.472662091255188},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4473848342895508},{"id":"https://openalex.org/keywords/tower","display_name":"Tower","score":0.44289037585258484},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4127134680747986},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32516324520111084},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0982162356376648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599368095397949},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6405697464942932},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6171541810035706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5199655294418335},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5123980641365051},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5014493465423584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4914897680282593},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.472662091255188},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4473848342895508},{"id":"https://openalex.org/C2777831296","wikidata":"https://www.wikidata.org/wiki/Q12518","display_name":"Tower","level":2,"score":0.44289037585258484},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4127134680747986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32516324520111084},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0982162356376648},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3463032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","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":39,"referenced_works":["https://openalex.org/W1558797106","https://openalex.org/W1610356397","https://openalex.org/W2027731328","https://openalex.org/W2101409192","https://openalex.org/W2152808281","https://openalex.org/W2158515176","https://openalex.org/W2295739661","https://openalex.org/W2512971201","https://openalex.org/W2640408555","https://openalex.org/W2648699835","https://openalex.org/W2741249238","https://openalex.org/W2774769176","https://openalex.org/W2798916557","https://openalex.org/W2912372357","https://openalex.org/W2912967843","https://openalex.org/W2915480215","https://openalex.org/W2936133855","https://openalex.org/W2950133940","https://openalex.org/W2963085847","https://openalex.org/W2963350250","https://openalex.org/W2964121744","https://openalex.org/W2972801466","https://openalex.org/W2982108874","https://openalex.org/W2982902390","https://openalex.org/W2987249037","https://openalex.org/W3014828506","https://openalex.org/W3023045848","https://openalex.org/W3035014997","https://openalex.org/W3035524453","https://openalex.org/W3038033387","https://openalex.org/W3038572442","https://openalex.org/W3080642298","https://openalex.org/W3098649723","https://openalex.org/W3099700870","https://openalex.org/W3103448498","https://openalex.org/W3104748221","https://openalex.org/W4245848455","https://openalex.org/W4297971002","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4214759293","https://openalex.org/W2948890638","https://openalex.org/W4390516098","https://openalex.org/W2129146436","https://openalex.org/W2032507829"],"abstract_inverted_index":{"The":[0],"two-tower":[1,21,46],"architecture":[2],"has":[3],"been":[4],"widely":[5],"applied":[6],"for":[7,16,63,74,88],"learning":[8],"item":[9,64,122],"and":[10,65,68,135,141],"user":[11,66],"representations,":[12],"which":[13,116],"is":[14,53],"important":[15],"large-scale":[17],"recommender":[18],"systems.":[19],"Many":[20],"models":[22,47],"are":[23],"trained":[24],"using":[25],"various":[26],"in-batch":[27],"negative":[28],"sampling":[29,109],"strategies,":[30],"where":[31],"the":[32,40,89,96,120,129,139,142],"effects":[33],"of":[34,42,61,72,119,144],"such":[35,101],"strategies":[36],"inherently":[37],"rely":[38],"on":[39,100],"size":[41,52],"mini-batches.":[43],"However,":[44],"training":[45,97],"with":[48],"a":[49,58,70,105],"large":[50,59],"batch":[51],"inefficient,":[54],"as":[55],"it":[56],"demands":[57],"volume":[60],"memory":[62],"contents":[67],"consumes":[69],"lot":[71],"time":[73],"feature":[75],"encoding.":[76],"Interestingly,":[77],"we":[78,103],"find":[79],"that":[80],"neural":[81],"encoders":[82],"can":[83],"output":[84],"relatively":[85],"stable":[86],"features":[87],"same":[90],"input":[91],"after":[92],"warming":[93],"up":[94],"in":[95],"process.":[98],"Based":[99],"facts,":[102],"propose":[104],"simple":[106],"yet":[107],"effective":[108],"strategy":[110],"called":[111],"Cross-Batch":[112],"Negative":[113],"Sampling":[114],"(CBNS),":[115],"takes":[117],"advantage":[118],"encoded":[121],"embeddings":[123],"from":[124],"recent":[125],"mini-batches":[126],"to":[127],"boost":[128],"model":[130],"training.":[131],"Both":[132],"theoretical":[133],"analysis":[134],"empirical":[136],"evaluations":[137],"demonstrate":[138],"effectiveness":[140],"efficiency":[143],"CBNS.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}