{"id":"https://openalex.org/W4411549678","doi":"https://doi.org/10.1145/3701716.3715576","title":"Scalable Overload-Aware Graph-Based Index Construction for 10-Billion-Scale Vector Similarity Search","display_name":"Scalable Overload-Aware Graph-Based Index Construction for 10-Billion-Scale Vector Similarity Search","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4411549678","doi":"https://doi.org/10.1145/3701716.3715576"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715576","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","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/A5102195711","display_name":"Yang Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Shi","raw_affiliation_strings":["Xiaohongshu Inc, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc, Shanghai, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113444955","display_name":"Yiping Sun","orcid":"https://orcid.org/0009-0000-9559-8268"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiping Sun","raw_affiliation_strings":["Xiaohongshu Inc, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc, Shanghai, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111256217","display_name":"Jiaolong Du","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaolong Du","raw_affiliation_strings":["Xiaohongshu Inc, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc, Shanghai, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100565225","display_name":"Xueping Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaocheng Zhong","raw_affiliation_strings":["Xiaohongshu Inc, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc, Shanghai, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109705656","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0009-0009-2335-4892"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["Xiaohongshu Inc, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc, Shanghai, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107062676","display_name":"Yao Hu","orcid":"https://orcid.org/0009-0006-1274-7111"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Hu","raw_affiliation_strings":["Xiaohongshu Inc, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc, Shanghai, China","institution_ids":["https://openalex.org/I862669128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102195711"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":4.6596,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94790693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1303","last_page":"1307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9976999759674072,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9879000186920166,"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":0.6712296009063721},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6362913250923157},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5785841941833496},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5309075117111206},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4569161534309387},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44766825437545776},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4137829542160034},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3364877700805664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2863960564136505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20825830101966858},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12747102975845337},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08161473274230957},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08103099465370178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712296009063721},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6362913250923157},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5785841941833496},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5309075117111206},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4569161534309387},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44766825437545776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4137829542160034},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3364877700805664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2863960564136505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20825830101966858},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12747102975845337},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08161473274230957},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08103099465370178},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715576","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1970647353","https://openalex.org/W1978112828","https://openalex.org/W2101051966","https://openalex.org/W2128703518","https://openalex.org/W2173213060","https://openalex.org/W2294518132","https://openalex.org/W2953247561","https://openalex.org/W2963469388","https://openalex.org/W3196481040","https://openalex.org/W4400909749","https://openalex.org/W4403577798"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"Approximate":[0],"Nearest":[1],"Neighbor":[2],"Search":[3],"(ANNS)":[4],"is":[5],"essential":[6],"for":[7,65],"modern":[8],"data-driven":[9],"applications":[10],"that":[11,80],"require":[12],"efficient":[13,89],"retrieval":[14],"of":[15,116,150,152],"top-k":[16],"results":[17],"from":[18],"massive":[19],"vector":[20,67],"databases.":[21],"Although":[22],"existing":[23,124],"graph-based":[24],"ANNS":[25,60],"algorithms":[26],"achieve":[27],"a":[28,72,96,114,135],"high":[29],"recall":[30],"rate":[31],"on":[32,110],"billion-scale":[33],"datasets,":[34],"their":[35,43],"slow":[36],"construction":[37,120],"speed":[38],"and":[39,147],"limited":[40],"scalability":[41],"hinder":[42],"applicability":[44],"to":[45,123],"large-scale":[46],"industrial":[47,137],"scenarios.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,93],"introduce":[53],"SOGAIC,":[54],"the":[55],"first":[56],"Scalable":[57],"Overload-Aware":[58],"Graph-Based":[59],"Index":[61],"Construction":[62],"system":[63],"tailored":[64],"ultra-large-scale":[66],"databases:":[68],"1)":[69],"We":[70],"propose":[71],"dynamic":[73],"data":[74],"partitioning":[75],"algorithm":[76],"with":[77,102],"overload":[78],"constraints":[79],"adaptively":[81],"introduces":[82],"overlaps":[83],"among":[84],"subsets;":[85],"2)":[86],"To":[87],"enable":[88],"distributed":[90],"subgraph":[91],"construction,":[92],"employ":[94],"an":[95,103],"load-balancing":[97],"task":[98],"scheduling":[99],"framework":[100],"combined":[101],"agglomerative":[104],"merging":[105],"strategy;":[106],"3)":[107],"Extensive":[108],"experiments":[109],"various":[111],"datasets":[112],"demonstrate":[113],"reduction":[115],"47.3%":[117],"in":[118,134],"average":[119],"time":[121],"compared":[122],"methods.":[125],"The":[126],"proposed":[127],"method":[128],"has":[129],"also":[130],"been":[131],"successfully":[132],"deployed":[133],"real-world":[136],"search":[138],"engine,":[139],"managing":[140],"over":[141],"10":[142],"billion":[143],"daily":[144],"updated":[145],"vectors":[146],"serving":[148],"hundreds":[149],"millions":[151],"users.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}