{"id":"https://openalex.org/W4392384310","doi":"https://doi.org/10.1145/3616855.3635774","title":"LEAD: Liberal Feature-based Distillation for Dense Retrieval","display_name":"LEAD: Liberal Feature-based Distillation for Dense Retrieval","publication_year":2024,"publication_date":"2024-03-04","ids":{"openalex":"https://openalex.org/W4392384310","doi":"https://doi.org/10.1145/3616855.3635774"},"language":"en","primary_location":{"id":"doi:10.1145/3616855.3635774","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635774","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635774","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635774","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037488877","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0001-8456-7925"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Sun","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441089","display_name":"Xiao Liu","orcid":null},"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":"Xiao 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/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/A5028114543","display_name":"Anlei Dong","orcid":"https://orcid.org/0000-0002-8241-4746"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anlei Dong","raw_affiliation_strings":["Microsoft, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037626945","display_name":"Jingwen Lu","orcid":"https://orcid.org/0000-0001-8208-898X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwen Lu","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022499183","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0003-4003-0290"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066134551","display_name":"Linjun Yang","orcid":"https://orcid.org/0000-0001-8843-1822"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linjun Yang","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090383211","display_name":"Rangan Majumder","orcid":"https://orcid.org/0000-0003-2430-575X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rangan Majumder","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674"},"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":"Nan Duan","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":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5037488877"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.4986,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60349088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"655","last_page":"664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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":0.9975000023841858,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9966999888420105,"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":0.7531191110610962},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7277028560638428},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6830027103424072},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6685464382171631},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5942778587341309},{"id":"https://openalex.org/keywords/lead","display_name":"Lead (geology)","score":0.5276761651039124},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5030547976493835},{"id":"https://openalex.org/keywords/ignorance","display_name":"Ignorance","score":0.4469630718231201},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4312403202056885},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4146279990673065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4091966152191162},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40882545709609985},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39088472723960876},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11059612035751343},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0829727053642273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531191110610962},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7277028560638428},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6830027103424072},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6685464382171631},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5942778587341309},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.5276761651039124},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5030547976493835},{"id":"https://openalex.org/C2778732403","wikidata":"https://www.wikidata.org/wiki/Q815577","display_name":"Ignorance","level":2,"score":0.4469630718231201},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4312403202056885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4146279990673065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4091966152191162},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40882545709609985},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39088472723960876},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11059612035751343},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0829727053642273},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3616855.3635774","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635774","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635774","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3616855.3635774","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635774","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635774","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8799999952316284}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392384310.pdf","grobid_xml":"https://content.openalex.org/works/W4392384310.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2296073425","https://openalex.org/W2740321901","https://openalex.org/W2887783173","https://openalex.org/W2945127593","https://openalex.org/W2954996726","https://openalex.org/W2997006708","https://openalex.org/W3021397474","https://openalex.org/W3034368386","https://openalex.org/W3099446234","https://openalex.org/W3099700870","https://openalex.org/W3108124733","https://openalex.org/W3110290422","https://openalex.org/W3138154797","https://openalex.org/W3154670582","https://openalex.org/W3155895380","https://openalex.org/W3157758108","https://openalex.org/W3172119680","https://openalex.org/W3177378457","https://openalex.org/W3184918446","https://openalex.org/W3206455169","https://openalex.org/W4206121183","https://openalex.org/W4225156005","https://openalex.org/W4281259526","https://openalex.org/W4307307675","https://openalex.org/W6600100092","https://openalex.org/W6600281463","https://openalex.org/W6609822380"],"related_works":["https://openalex.org/W4387185014","https://openalex.org/W4387906132","https://openalex.org/W4321603833","https://openalex.org/W4321603789","https://openalex.org/W588868971","https://openalex.org/W4200350283","https://openalex.org/W4283215876","https://openalex.org/W4399826833","https://openalex.org/W4253298899","https://openalex.org/W4321603797"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1,66],"is":[2,84,128],"often":[3],"used":[4,31],"to":[5,13,41],"transfer":[6],"knowledge":[7],"from":[8,34],"a":[9,14,63],"strong":[10],"teacher":[11,78],"model":[12,56,79,96],"relatively":[15],"weak":[16],"student":[17,81],"model.":[18],"Traditional":[19],"methods":[20,23,28,49],"include":[21],"response-based":[22],"and":[24,55,80,88,121],"feature-based":[25,48,65],"methods.":[26],"Response-based":[27],"are":[29],"widely":[30],"but":[32],"suffer":[33],"lower":[35],"upper":[36],"limits":[37],"of":[38,44,77,103],"performance":[39],"due":[40],"their":[42],"ignorance":[43],"intermediate":[45,75],"signals,":[46],"while":[47],"have":[50],"constraints":[51],"on":[52,92,105],"vocabularies,":[53,93],"tokenizers":[54],"architectures.":[57,97],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"liberal":[64],"method":[67],"(LEAD).":[68],"LEAD":[69,104],"aligns":[70],"the":[71,74,101],"distribution":[72],"between":[73],"layers":[76],"model,":[82],"which":[83],"effective,":[85],"extendable,":[86],"portable":[87],"has":[89],"no":[90],"requirements":[91],"tokenizers,":[94],"or":[95],"Extensive":[98],"experiments":[99],"show":[100],"effectiveness":[102],"widely-used":[106],"benchmarks,":[107],"including":[108],"MS":[109,117],"MARCO":[110,118],"Passage":[111],"Ranking,":[112],"TREC":[113,122],"2019":[114],"DL":[115,124],"Track,":[116],"Document":[119],"Ranking":[120],"2020":[123],"Track.":[125],"Our":[126],"code":[127],"available":[129],"in":[130],"https://github.com/microsoft/SimXNS/tree/main/LEAD.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}