{"id":"https://openalex.org/W4292955407","doi":"https://doi.org/10.1145/3511808.3557527","title":"A Contrastive Pre-training Approach to Discriminative Autoencoder for Dense Retrieval","display_name":"A Contrastive Pre-training Approach to Discriminative Autoencoder for Dense Retrieval","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4292955407","doi":"https://doi.org/10.1145/3511808.3557527"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557527","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557527","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557527","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557527","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056848863","display_name":"Xinyu Ma","orcid":"https://orcid.org/0000-0002-5511-9370"},"institutions":[{"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":true,"raw_author_name":"Xinyu Ma","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009898523","display_name":"Ruqing Zhang","orcid":"https://orcid.org/0000-0003-4294-2541"},"institutions":[{"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":"Ruqing Zhang","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109736354","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-2793-3893"},"institutions":[{"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":["CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006971161","display_name":"Yixing Fan","orcid":"https://orcid.org/0000-0003-4317-2702"},"institutions":[{"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":"Yixing Fan","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"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":"Xueqi Cheng","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056848863"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5216,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63328034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4314","last_page":"4318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973999857902527,"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/discriminative-model","display_name":"Discriminative model","score":0.8774807453155518},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8431769013404846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887826561927795},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6621665358543396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6473672389984131},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6367802619934082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5220022797584534},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46181926131248474},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44788262248039246},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4363471269607544},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42794132232666016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3840159475803375},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.29064610600471497},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1088574230670929},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0934324860572815}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8774807453155518},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8431769013404846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887826561927795},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6621665358543396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6473672389984131},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6367802619934082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5220022797584534},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46181926131248474},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44788262248039246},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4363471269607544},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42794132232666016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3840159475803375},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29064610600471497},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1088574230670929},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0934324860572815},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3511808.3557527","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557527","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557527","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.09846","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.09846","pdf_url":"https://arxiv.org/pdf/2208.09846","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3511808.3557527","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557527","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557527","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1084062135","display_name":null,"funder_award_id":"20144310","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G1101359642","display_name":null,"funder_award_id":"No. 62006218 and 61902381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1420860423","display_name":null,"funder_award_id":"62006218 and 61902381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317933164","display_name":null,"funder_award_id":"No. 62006218","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4758593323","display_name":null,"funder_award_id":"20144310, and 2021100","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G7539905487","display_name":null,"funder_award_id":"202110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8003451188","display_name":null,"funder_award_id":"20200121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4292955407.pdf","grobid_xml":"https://content.openalex.org/works/W4292955407.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2146950091","https://openalex.org/W3093570284","https://openalex.org/W3105816068","https://openalex.org/W3115195983","https://openalex.org/W3152562554","https://openalex.org/W3155895380","https://openalex.org/W3212725701","https://openalex.org/W4206121183","https://openalex.org/W4223512675","https://openalex.org/W4224865658","https://openalex.org/W4252076394"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2116862786"],"abstract_inverted_index":{"Dense":[0],"retrieval":[1],"(DR)":[2],"has":[3,58],"shown":[4,28],"promising":[5],"results":[6,171],"in":[7,21,83,93,125,164],"information":[8],"retrieval.":[9,190],"In":[10],"essence,":[11],"DR":[12,50],"requires":[13],"high-quality":[14,40],"text":[15,41,124,140],"representations":[16,72],"to":[17,102,118,167],"support":[18],"effective":[19],"search":[20],"the":[22,44,59,63,67,85,90,131,156,161,179],"representation":[23],"space.":[24],"Recent":[25],"studies":[26],"have":[27],"that":[29,150,173],"pre-trained":[30,186],"autoencoder-based":[31,181],"language":[32,182],"models":[33,183,187],"with":[34,107],"a":[35,54,98,104,108,126],"weak":[36,55],"decoder":[37,57],"can":[38,154,176],"provide":[39],"representations,":[42],"boosting":[43],"effectiveness":[45],"and":[46,129,159,184],"few-shot":[47],"ability":[48,69],"of":[49,70,122,134,138],"models.":[51],"However,":[52],"even":[53],"autoregressive":[56],"bypass":[60],"effect":[61],"on":[62],"encoder.":[64],"More":[65],"importantly,":[66],"discriminative":[68,105,168],"learned":[71],"may":[73],"be":[74],"limited":[75],"since":[76],"each":[77],"token":[78],"is":[79,117],"treated":[80],"equally":[81],"important":[82],"decoding":[84],"input":[86,123],"texts.":[87],"To":[88],"address":[89],"above":[91],"problems,":[92],"this":[94],"paper,":[95],"we":[96],"propose":[97],"contrastive":[99,152],"pre-training":[100],"approach":[101],"learn":[103],"autoencoder":[106],"lightweight":[109],"multi-layer":[110],"perception":[111],"(MLP)":[112],"decoder.":[113],"The":[114],"basic":[115],"idea":[116],"generate":[119],"word":[120,132],"distributions":[121,133],"non-autoregressive":[127],"fashion":[128],"pull":[130],"two":[135],"masked":[136],"versions":[137],"one":[139],"close":[141],"while":[142],"pushing":[143],"away":[144],"from":[145],"others.":[146],"We":[147],"theoretically":[148],"show":[149,172],"our":[151,174],"strategy":[153],"suppress":[155],"common":[157],"words":[158,163],"highlight":[160],"representative":[162],"decoding,":[165],"leading":[166],"representations.":[169],"Empirical":[170],"method":[175],"significantly":[177],"outperform":[178],"state-of-the-art":[180],"other":[185],"for":[188],"dense":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2022-08-24T00:00:00"}