{"id":"https://openalex.org/W4290875540","doi":"https://doi.org/10.1145/3534678.3539414","title":"BLISS: A Billion scale Index using Iterative Re-partitioning","display_name":"BLISS: A Billion scale Index using Iterative Re-partitioning","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290875540","doi":"https://doi.org/10.1145/3534678.3539414"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539414","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539414","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5077386816","display_name":"Gaurav Gupta","orcid":"https://orcid.org/0000-0002-5192-4428"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gaurav Gupta","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059158692","display_name":"Tharun Medini","orcid":"https://orcid.org/0009-0000-0410-2977"},"institutions":[{"id":"https://openalex.org/I2802091258","display_name":"Third Way","ror":"https://ror.org/047vwpj87","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802091258"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tharun Medini","raw_affiliation_strings":["ThirdAI Corp., Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"ThirdAI Corp., Houston, TX, USA","institution_ids":["https://openalex.org/I2802091258"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024993683","display_name":"Anshumali Shrivastava","orcid":"https://orcid.org/0000-0002-5042-2856"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshumali Shrivastava","raw_affiliation_strings":["Rice University & ThirdAI Corp., Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University & ThirdAI Corp., Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000245150","display_name":"Alexander J. Smola","orcid":"https://orcid.org/0000-0002-7963-4721"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander J. Smola","raw_affiliation_strings":["Amazon Web Services, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077386816"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":0.7224,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.79331242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"486","last_page":"495"},"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":0.9994999766349792,"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":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9914000034332275,"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/bliss","display_name":"BLISS","score":0.9286372661590576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806273698806763},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.649347186088562},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6062979102134705},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.46692582964897156},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43972691893577576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3686192035675049},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3660048842430115},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16340842843055725}],"concepts":[{"id":"https://openalex.org/C2780658912","wikidata":"https://www.wikidata.org/wiki/Q2877155","display_name":"BLISS","level":2,"score":0.9286372661590576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806273698806763},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.649347186088562},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6062979102134705},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.46692582964897156},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43972691893577576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3686192035675049},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3660048842430115},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16340842843055725},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539414","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539414","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8590205217","display_name":null,"funder_award_id":"IIS-1652131","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W97540112","https://openalex.org/W125936143","https://openalex.org/W1502916507","https://openalex.org/W2097117768","https://openalex.org/W2117702591","https://openalex.org/W2124509324","https://openalex.org/W2132234208","https://openalex.org/W2136189984","https://openalex.org/W2152437528","https://openalex.org/W2362855512","https://openalex.org/W2744136723","https://openalex.org/W2752782242","https://openalex.org/W2788125153","https://openalex.org/W2906963924","https://openalex.org/W2949985202","https://openalex.org/W2962771342","https://openalex.org/W2963469388","https://openalex.org/W2998241033","https://openalex.org/W2998702515","https://openalex.org/W3021397474","https://openalex.org/W3080802002","https://openalex.org/W4212774754","https://openalex.org/W4236965008","https://openalex.org/W4254197176","https://openalex.org/W6629956336"],"related_works":["https://openalex.org/W2393932274","https://openalex.org/W2364921833","https://openalex.org/W1525643724","https://openalex.org/W2067938758","https://openalex.org/W2382623646","https://openalex.org/W3087771547","https://openalex.org/W2333420780","https://openalex.org/W2375199418","https://openalex.org/W2348101466","https://openalex.org/W2368437561"],"abstract_inverted_index":{"Representation":[0],"learning":[1,95],"has":[2],"transformed":[3],"the":[4,13,32,45,55,96,101,108,114,154,170,182,222,254,260],"problem":[5],"of":[6,11,16,86,92,156,256],"information":[7],"retrieval":[8,33,145],"into":[9],"one":[10],"finding":[12],"approximate":[14],"set":[15],"nearest":[17],"neighbors":[18],"in":[19,50,208],"a":[20,59,69,215,276],"high":[21,127],"dimensional":[22],"vector":[23],"space.":[24],"With":[25],"limited":[26],"hardware":[27],"resources":[28],"and":[29,44,148,160,176,186,195,240,251],"time-critical":[30],"queries,":[31],"engines":[34],"face":[35],"an":[36],"inherent":[37],"tension":[38],"between":[39],"latency,":[40],"accuracy,":[41],"scalability,":[42],"compactness,":[43],"ability":[46],"to":[47,82,84,135],"load":[48,124],"balance":[49],"distributed":[51,247],"settings.":[52],"To":[53,105],"improve":[54],"trade-off,":[56],"we":[57,158],"propose":[58],"new":[60],"algorithm,":[61],"called":[62],"BaLanced":[63],"Index":[64],"for":[65,142,179,221,246,249,268],"Scalable":[66],"Search":[67],"(BLISS),":[68],"highly":[70],"tunable":[71],"indexing":[72,174],"algorithm":[73],"with":[74,126,164,181,231,274],"enviably":[75],"small":[76],"index":[77,161,177],"sizes,":[78],"making":[79,205,243],"it":[80,206,244],"easy":[81],"scale":[83],"billions":[85],"vectors.":[87],"It":[88],"iteratively":[89],"refines":[90],"partitions":[91],"items":[93],"by":[94],"relevant":[97],"buckets":[98,109],"directly":[99],"from":[100],"query-item":[102],"relevance":[103],"data.":[104],"ensure":[106],"that":[107,120],"are":[110],"balanced,":[111],"BLISS":[112,121,138,180,198,227,236,258],"uses":[113],"power-of-K":[115],"choices":[116],"strategy.":[117],"We":[118,168],"show":[119],"provides":[122],"superior":[123],"balancing":[125],"probability":[128],"(and":[129],"under":[130],"very":[131],"benign":[132],"assumptions).":[133],"Due":[134],"its":[136],"design,":[137],"can":[139],"be":[140],"employed":[141],"both":[143,238],"near-neighbor":[144],"(ANN":[146],"problem)":[147],"extreme":[149],"classification":[150],"(XML":[151],"problem).":[152],"For":[153,253],"case":[155,255],"ANN,":[157],"train":[159],"4":[162],"datasets":[163,273],"billion":[165],"vectors":[166],"each.":[167],"compare":[169],"recall,":[171],"inference":[172,217,269],"time,":[173,175],"size":[178],"two":[183],"most":[184],"popular":[185,271],"well-optimized":[187],"libraries-":[188],"Hierarchical":[189],"Navigable":[190],"Small":[191],"World":[192],"(HNSW)":[193],"graph":[194],"Facebook's":[196],"FAISS.":[197],"requires":[199],"100x":[200],"lesser":[201],"RAM":[202],"than":[203],"HNSW,":[204],"fit":[207],"memory":[209,234],"on":[210,270],"commodity":[211],"machines":[212],"while":[213,264],"taking":[214],"similar":[216,229],"time":[218],"as":[219],"HNSW":[220],"same":[223],"recall.":[224],"Against":[225],"FAISS-IVF,":[226],"achieves":[228],"performance":[230],"3-4x":[232],"less":[233],"requirement.":[235],"is":[237],"data":[239],"model":[241],"parallel,":[242],"ideal":[245],"implementation":[248],"training":[250],"inference.":[252],"XML,":[257],"surpasses":[259],"best":[261],"baselines'":[262],"precision":[263],"being":[265],"5x":[266],"faster":[267],"multi-label":[272],"half":[275],"million":[277],"classes.":[278]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}