{"id":"https://openalex.org/W4221159373","doi":"https://doi.org/10.1145/3485447.3511957","title":"Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval","display_name":"Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4221159373","doi":"https://doi.org/10.1145/3485447.3511957"},"language":"en","primary_location":{"id":"doi:10.1145/3485447.3511957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3511957","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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 ACM Web Conference 2022","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, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, 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, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102446548","display_name":"Weihao Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihao Han","raw_affiliation_strings":["Microsoft Search Technology Center Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, 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 Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, 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, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"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, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037831162","display_name":"Chaozhuo Li","orcid":"https://orcid.org/0000-0002-9867-1712"},"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":"Chaozhuo Li","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694346","display_name":"Hao Sun","orcid":"https://orcid.org/0009-0002-6439-7337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["Microsoft Search Technology Center Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017295812","display_name":"Denvy Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denvy Deng","raw_affiliation_strings":["Microsoft Search Technology Center Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068728111","display_name":"Liang\u2010Jie Zhang","orcid":"https://orcid.org/0000-0002-6219-0853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangjie Zhang","raw_affiliation_strings":["Microsoft Search Technology Center Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883106","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0002-8056-3334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Microsoft Search Technology Center Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, China","institution_ids":[]}]},{"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, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5044147794"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.9595,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83074291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"296"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994999766349792,"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":0.9991000294685364,"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":0.8103379607200623},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5765289068222046},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.564045250415802},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4976556599140167},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49422648549079895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44088226556777954},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14891815185546875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103379607200623},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5765289068222046},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.564045250415802},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4976556599140167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49422648549079895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44088226556777954},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14891815185546875},{"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:10.1145/3485447.3511957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485447.3511957","pdf_url":null,"source":{"id":"https://openalex.org/S4363608783","display_name":"Proceedings of the ACM Web Conference 2022","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 ACM Web Conference 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5},{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G5620609558","display_name":null,"funder_award_id":"U1936104","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":24,"referenced_works":["https://openalex.org/W2077815765","https://openalex.org/W2096077837","https://openalex.org/W2124509324","https://openalex.org/W2132234208","https://openalex.org/W2162006472","https://openalex.org/W2186845332","https://openalex.org/W2913954081","https://openalex.org/W2950960796","https://openalex.org/W2963213349","https://openalex.org/W2963469388","https://openalex.org/W2983848182","https://openalex.org/W3011411500","https://openalex.org/W3012754345","https://openalex.org/W3035524453","https://openalex.org/W3036320503","https://openalex.org/W3098468692","https://openalex.org/W3099700870","https://openalex.org/W3154670582","https://openalex.org/W3155895380","https://openalex.org/W3157758108","https://openalex.org/W3168875417","https://openalex.org/W3172750682","https://openalex.org/W3177415603","https://openalex.org/W3212208733"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W2037549926","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W3170260665"],"abstract_inverted_index":{"Ad-hoc":[0],"search":[1,30,121,217],"calls":[2],"for":[3,84,97,119,162],"the":[4,14,44,56,74,89,102,126,131,134,142,147,153,157,163,178],"selection":[5],"of":[6,59,104,122,144,165],"appropriate":[7],"answers":[8],"from":[9,146],"a":[10,19,39,107,214],"massive-scale":[11,185],"corpus.":[12,61,207],"Nowadays,":[13],"embedding-based":[15],"retrieval":[16,105],"(EBR)":[17],"becomes":[18],"promising":[20],"solution,":[21],"where":[22,73],"deep":[23],"learning":[24,164],"based":[25],"document":[26],"representation":[27],"and":[28,80,88,156,167,200,227],"ANN":[29,45],"techniques":[31],"are":[32,78,93,116,137,160],"allied":[33],"to":[34,51,140,173,177,194,202,213],"handle":[35],"this":[36,63,67],"task.":[37],"However,":[38],"major":[40,215],"challenge":[41],"is":[42,111,211,232],"that":[43],"index":[46],"can":[47],"be":[48],"too":[49],"large":[50],"fit":[52],"into":[53],"memory,":[54],"given":[55],"considerable":[57],"size":[58],"answer":[60],"In":[62],"work,":[64],"we":[65],"tackle":[66],"problem":[68],"with":[69,187,192,219],"Bi-Granular":[70],"Document":[71],"Representation,":[72],"lightweight":[75],"sparse":[76,114,132,166],"embeddings":[77,92,115,136],"indexed":[79],"standby":[81],"in":[82,95,190],"memory":[83],"coarse-grained":[85],"candidate":[86,127],"search,":[87],"heavyweight":[90],"dense":[91,135,168],"hosted":[94],"disk":[96],"fine-grained":[98],"post":[99],"verification.":[100],"For":[101],"best":[103],"accuracy,":[106],"Progressive":[108],"Optimization":[109],"framework":[110],"designed.":[112],"The":[113],"learned":[117,139],"ahead":[118],"high-quality":[120],"candidates.":[123,149],"Conditioned":[124],"on":[125,197,205,222],"distribution":[128],"induced":[129],"by":[130],"embeddings,":[133,169],"continuously":[138],"optimize":[141],"discrimination":[143],"ground-truth":[145],"shortlisted":[148],"Besides,":[150,208],"two":[151],"techniques:":[152],"contrastive":[154],"quantization":[155],"locality-centric":[158],"sampling":[159],"introduced":[161],"which":[170],"substantially":[171],"contribute":[172],"their":[174],"performances.":[175],"Thanks":[176],"above":[179],"features,":[180],"our":[181],"method":[182,210],"effectively":[183],"handles":[184],"EBR":[186],"strong":[188],"advantages":[189],"accuracy:":[191],"up":[193,201],"recall":[195,203],"gain":[196,204],"million-scale":[198],"corpus,":[199],"billion-scale":[206],"Our":[209,230],"applied":[212],"sponsored":[216],"platform":[218],"substantial":[220],"gains":[221],"revenue":[223],"(),":[224],"Recall":[225],"()":[226],"CTR":[228],"().":[229],"code":[231],"available":[233],"at":[234],"https://github.com/microsoft/BiDR.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}