{"id":"https://openalex.org/W4284685333","doi":"https://doi.org/10.1145/3477495.3531799","title":"Distill-VQ","display_name":"Distill-VQ","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4284685333","doi":"https://doi.org/10.1145/3477495.3531799"},"language":"en","primary_location":{"id":"doi:10.1145/3477495.3531799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531799","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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 45th 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/A5044147794","display_name":"Shitao Xiao","orcid":"https://orcid.org/0000-0003-2567-6843"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shitao Xiao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423656","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0001-7765-8466"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022072215","display_name":"Weihao Han","orcid":"https://orcid.org/0000-0002-5533-6455"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihao Han","raw_affiliation_strings":["Microsoft Search Technology Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055260255","display_name":"Jianjin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianjin Zhang","raw_affiliation_strings":["Microsoft Search Technology Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085254654","display_name":"Defu Lian","orcid":"https://orcid.org/0000-0002-3507-9607"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Defu Lian","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041448669","display_name":"Yeyun Gong","orcid":"https://orcid.org/0000-0001-9954-9674"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeyun Gong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340139","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0001-8732-8049"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024572557","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-1044-7821"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037488877","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0001-8456-7925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["Microsoft Search Technology Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014615052","display_name":"Yingxia Shao","orcid":"https://orcid.org/0000-0002-8559-2628"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingxia Shao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5044147794"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.6152,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.89006388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1513","last_page":"1523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973000288009644,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9894999861717224,"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":0.7222080230712891},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6782209873199463},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5994706749916077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5807554125785828},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5730679035186768},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5170603394508362},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4781404733657837},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43298447132110596},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4271705746650696},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.357298344373703},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11868029832839966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222080230712891},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6782209873199463},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5994706749916077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5807554125785828},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5730679035186768},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5170603394508362},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4781404733657837},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43298447132110596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4271705746650696},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.357298344373703},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11868029832839966},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":1,"locations":[{"id":"doi:10.1145/3477495.3531799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531799","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8602696467","display_name":null,"funder_award_id":"U1936104, 62192784, 62022077, 61976198","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W2077815765","https://openalex.org/W2108862644","https://openalex.org/W2124509324","https://openalex.org/W2132234208","https://openalex.org/W2186845332","https://openalex.org/W2738649458","https://openalex.org/W2912924812","https://openalex.org/W2913954081","https://openalex.org/W2963213349","https://openalex.org/W2963265099","https://openalex.org/W2998702515","https://openalex.org/W3012754345","https://openalex.org/W3035160371","https://openalex.org/W3036320503","https://openalex.org/W3094444847","https://openalex.org/W3098468692","https://openalex.org/W3099700870","https://openalex.org/W3155624780","https://openalex.org/W3156978171","https://openalex.org/W3172750682","https://openalex.org/W3209791570","https://openalex.org/W3212208733","https://openalex.org/W4221159373","https://openalex.org/W4285603655"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2085384747","https://openalex.org/W1539956819","https://openalex.org/W2088166309","https://openalex.org/W1891216533","https://openalex.org/W2037549926","https://openalex.org/W2093152993","https://openalex.org/W4312133475","https://openalex.org/W4238976562","https://openalex.org/W3209251257"],"abstract_inverted_index":{"Vector":[0],"quantization":[1],"(VQ)":[2],"based":[3,22,229],"ANN":[4,230],"indexes,":[5],"such":[6,57,84,170],"as":[7,143,159],"Inverted":[8],"File":[9],"System":[10],"(IVF)":[11],"and":[12,30,50,87,129,263,277],"Product":[13],"Quantization":[14],"(PQ),":[15],"have":[16],"been":[17],"widely":[18],"applied":[19],"to":[20,26,37,89,150,165,191,204],"embedding":[21],"document":[23],"retrieval":[24,79,92,179,206],"thanks":[25],"the":[27,39,43,46,51,63,70,91,112,125,138,147,151,160,167,172,178,182,197,205,213,225,237,271],"competitive":[28],"time":[29],"memory":[31],"efficiency.":[32],"Originally,":[33],"VQ":[34,155,228,273],"is":[35,60,109,189,240,281],"learned":[36,164],"minimize":[38,90],"reconstruction":[40],"loss,":[41],"i.e.,":[42],"distortions":[44],"between":[45],"original":[47],"dense":[48,139,183],"embeddings":[49,53,140,174],"reconstructed":[52,173],"after":[54],"quantization.":[55],"Unfortunately,":[56],"an":[58],"objective":[59],"inconsistent":[61],"with":[62,104],"goal":[64],"of":[65,78,114,127,181,216,227],"selecting":[66],"ground-truth":[67,105],"documents":[68],"for":[69,212,224,245],"input":[71],"query,":[72],"which":[73,123,145,162,201,219,249],"may":[74,175,220],"cause":[75],"severe":[76],"loss":[77,93],"quality.":[80,207],"Recent":[81],"works":[82],"identify":[83],"a":[85,132,243],"defect,":[86],"propose":[88,121],"through":[94],"contrastive":[95],"learning.":[96],"However,":[97],"these":[98],"methods":[99,274],"intensively":[100],"rely":[101],"on":[102,260],"queries":[103],"documents,":[106],"whose":[107],"performance":[108],"limited":[110],"by":[111],"insufficiency":[113],"labeled":[115,238],"data.":[116],"In":[117,136],"this":[118],"paper,":[119],"we":[120],"Distill-VQ,":[122,137],"unifies":[124],"learning":[126,226],"IVF":[128],"PQ":[130],"within":[131],"knowledge":[133,217],"distillation":[134],"framework.":[135],"are":[141,157,163,258],"leveraged":[142],"\"teachers'',":[144],"predict":[146],"query's":[148],"relevance":[149],"sampled":[152],"documents.":[153],"The":[154,256],"modules":[156],"treated":[158],"\"students'',":[161],"reproduce":[166],"predicted":[168],"relevance,":[169],"that":[171,236],"fully":[176],"preserve":[177],"result":[180],"embeddings.":[184],"By":[185],"doing":[186],"so,":[187],"Distill-VQ":[188,268],"able":[190],"derive":[192],"substantial":[193],"training":[194],"signals":[195],"from":[196],"massive":[198],"unlabeled":[199],"data,":[200],"significantly":[202],"contributes":[203],"We":[208,232],"perform":[209],"comprehensive":[210],"explorations":[211],"optimal":[214],"conduct":[215],"distillation,":[218],"provide":[221],"useful":[222],"insights":[223],"index.":[231],"also":[233],"experimentally":[234],"show":[235],"data":[239],"no":[241],"longer":[242],"necessity":[244],"high-quality":[246],"vector":[247],"quantization,":[248],"indicates":[250],"Distill-VQ's":[251],"strong":[252],"applicability":[253],"in":[254,275],"practice.":[255],"evaluations":[257],"performed":[259],"MS":[261],"MARCO":[262],"Natural":[264],"Questions":[265],"benchmarks,":[266],"where":[267],"notably":[269],"outperforms":[270],"SOTA":[272],"Recall":[276],"MRR.":[278],"Our":[279],"code":[280],"avaliable":[282],"at":[283],"https://github.com/staoxiao/LibVQ.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2022-07-08T00:00:00"}