{"id":"https://openalex.org/W3155895380","doi":"https://doi.org/10.1145/3404835.3462880","title":"Optimizing Dense Retrieval Model Training with Hard Negatives","display_name":"Optimizing Dense Retrieval Model Training with Hard Negatives","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3155895380","doi":"https://doi.org/10.1145/3404835.3462880","mag":"3155895380"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462880","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462880","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":"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/A5023520034","display_name":"Jingtao Zhan","orcid":"https://orcid.org/0000-0002-7253-5245"},"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":true,"raw_author_name":"Jingtao Zhan","raw_affiliation_strings":["BNRist, DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BNRist, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072119199","display_name":"Jiaxin Mao","orcid":"https://orcid.org/0000-0002-9257-5498"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Mao","raw_affiliation_strings":["GSAI, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"GSAI, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668121","display_name":"Yiqun Liu","orcid":"https://orcid.org/0000-0002-0140-4512"},"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":"Yiqun Liu","raw_affiliation_strings":["BNRist, DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BNRist, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["University of Chinese Academy of Sciences & Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"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":"Min Zhang","raw_affiliation_strings":["BNRist, DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BNRist, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760812","display_name":"Shaoping Ma","orcid":"https://orcid.org/0000-0002-8762-8268"},"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":"Shaoping Ma","raw_affiliation_strings":["BNRist, DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BNRist, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023520034"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":26.8786,"has_fulltext":false,"cited_by_count":230,"citation_normalized_percentile":{"value":0.99720529,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1503","last_page":"1512"},"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":0.9988999962806702,"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":0.9988999962806702,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8574143648147583},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.761137843132019},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6767330169677734},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6426449418067932},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5324764251708984},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.525288462638855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4845077395439148},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4738752543926239},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.4547249376773834},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44109973311424255},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4396893084049225},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3839390277862549}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574143648147583},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.761137843132019},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6767330169677734},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6426449418067932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5324764251708984},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.525288462638855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4845077395439148},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4738752543926239},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.4547249376773834},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44109973311424255},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4396893084049225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3839390277862549},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3462880","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462880","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7015724984","display_name":null,"funder_award_id":"2018YFC0831700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2001832483","https://openalex.org/W2014415866","https://openalex.org/W2115584760","https://openalex.org/W2124509324","https://openalex.org/W2152790380","https://openalex.org/W2170245882","https://openalex.org/W2197084977","https://openalex.org/W2604738573","https://openalex.org/W2626778328","https://openalex.org/W2750779823","https://openalex.org/W2896457183","https://openalex.org/W2899154813","https://openalex.org/W2998702515","https://openalex.org/W3013936901","https://openalex.org/W3021397474","https://openalex.org/W3036320503","https://openalex.org/W3098468692","https://openalex.org/W3130740619","https://openalex.org/W4251326898","https://openalex.org/W4300011764"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W4386005305","https://openalex.org/W4386214543","https://openalex.org/W3082051559","https://openalex.org/W1969988626","https://openalex.org/W1682621979","https://openalex.org/W2141301039","https://openalex.org/W2152863486"],"abstract_inverted_index":{"Ranking":[0,186],"has":[1,19],"always":[2],"been":[3],"one":[4,214],"of":[5,44,78,95,194,244],"the":[6,15,21,34,42,76,139,192,204,218,248],"top":[7],"concerns":[8],"in":[9,30,102,150],"information":[10],"retrieval":[11,23,31,227],"researches.":[12],"For":[13],"decades,":[14],"lexical":[16],"matching":[17],"signal":[18,29],"dominated":[20],"ad-hoc":[22],"process,":[24],"but":[25],"solely":[26],"using":[27],"this":[28],"may":[32],"cause":[33],"vocabulary":[35],"mismatch":[36],"problem.":[37],"In":[38],"recent":[39],"years,":[40],"with":[41,211],"development":[43],"representation":[45],"learning":[46],"techniques,":[47],"many":[48,147,159],"researchers":[49],"turn":[50],"to":[51,127,215,247],"Dense":[52],"Retrieval":[53,176],"(DR)":[54],"models":[55,64,124],"for":[56,89,93,122,174,183],"better":[57,134],"ranking":[58,219],"performance.":[59,220,250],"Although":[60],"several":[61],"existing":[62,160,238],"DR":[63,123,195],"have":[65],"already":[66],"obtained":[67],"promising":[68],"results,":[69],"their":[70],"performance":[71,106],"improvement":[72,107],"heavily":[73],"relies":[74],"on":[75,112,223],"sampling":[77,83,132,209],"training":[79,120,161,167,181,196],"examples.":[80],"Many":[81],"effective":[82],"strategies":[84,121,168],"are":[85,146],"not":[86],"efficient":[87],"enough":[88],"practical":[90],"usage,":[91],"and":[92,104,125,178,241],"most":[94],"them,":[96],"there":[97,145],"still":[98],"lacks":[99],"theoretical":[100],"analysis":[101],"how":[103],"why":[105,129],"happens.":[108],"To":[109],"shed":[110],"light":[111],"these":[113],"research":[114],"questions,":[115],"we":[116,141,164],"theoretically":[117],"investigate":[118],"different":[119],"try":[126],"explain":[128],"hard":[130,152,207],"negative":[131,153,208],"performs":[133],"than":[135],"random":[136,200],"sampling.":[137],"Through":[138],"analysis,":[140],"also":[142],"find":[143],"that":[144,231],"potential":[148],"risks":[149],"static":[151,206],"sampling,":[154],"which":[155],"is":[156],"employed":[157],"by":[158,198],"methods.":[162],"Therefore,":[163],"propose":[165],"two":[166,224],"named":[169],"a":[170,179,212,242],"Stable":[171],"Training":[172],"Algorithm":[173,182],"dense":[175],"(STAR)":[177],"query-side":[180],"Directly":[184],"Optimizing":[185],"pErformance":[187],"(ADORE),":[188],"respectively.":[189],"STAR":[190],"improves":[191],"stability":[193],"process":[197],"introducing":[199],"negatives.":[201],"ADORE":[202],"replaces":[203],"widely-adopted":[205],"method":[210],"dynamic":[213],"directly":[216],"optimize":[217],"Experimental":[221],"results":[222],"publicly":[225],"available":[226],"benchmark":[228],"datasets":[229],"show":[230],"either":[232],"strategy":[233],"gains":[234],"significant":[235],"improvements":[236],"over":[237],"competitive":[239],"baselines":[240],"combination":[243],"them":[245],"leads":[246],"best":[249]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":61},{"year":2023,"cited_by_count":75},{"year":2022,"cited_by_count":44},{"year":2021,"cited_by_count":12}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}