{"id":"https://openalex.org/W7151444570","doi":"https://doi.org/10.1145/3786694","title":"Scalable Clustering Over High Dimensional Vector Streams","display_name":"Scalable Clustering Over High Dimensional Vector Streams","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7151444570","doi":"https://doi.org/10.1145/3786694"},"language":"en","primary_location":{"id":"doi:10.1145/3786694","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786694","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3786694","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Han Han","orcid":"https://orcid.org/0009-0007-0539-9013"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Han","raw_affiliation_strings":["University of Arizona, Tucson, USA"],"raw_orcid":"https://orcid.org/0009-0007-0539-9013","affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050010654","display_name":"Beichuan Zhang","orcid":"https://orcid.org/0009-0001-5333-8465"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beichuan Zhang","raw_affiliation_strings":["University of Arizona, Tucson, USA"],"raw_orcid":"https://orcid.org/0009-0001-5333-8465","affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lei Cao","orcid":"https://orcid.org/0000-0001-9909-8607"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Cao","raw_affiliation_strings":["University of Arizona, Tucson, USA"],"raw_orcid":"https://orcid.org/0000-0001-9909-8607","affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, USA","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138006243"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38926747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.5080999732017517,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.5080999732017517,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.07320000231266022,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.04910000041127205,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7404999732971191},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6399000287055969},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.522599995136261},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5069000124931335},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49070000648498535},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.4903999865055084},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.483599990606308},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42719998955726624},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.40149998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505999803543091},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7404999732971191},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6801999807357788},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6399000287055969},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49070000648498535},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.38600000739097595},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.263700008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786694","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786694","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3786694","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786694","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5799664258956909}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W182707955","https://openalex.org/W1984107911","https://openalex.org/W1987971958","https://openalex.org/W2020498246","https://openalex.org/W2047443612","https://openalex.org/W2054912417","https://openalex.org/W2092335550","https://openalex.org/W2145360759","https://openalex.org/W2165533158","https://openalex.org/W2296746822","https://openalex.org/W2343620495","https://openalex.org/W2404779194","https://openalex.org/W2525159801","https://openalex.org/W2542543501","https://openalex.org/W2585280277","https://openalex.org/W2619782615","https://openalex.org/W2925837647","https://openalex.org/W3002330681","https://openalex.org/W3004860284","https://openalex.org/W3108674801","https://openalex.org/W3133323004","https://openalex.org/W3200728138","https://openalex.org/W4205390421","https://openalex.org/W4300490703","https://openalex.org/W4393320781","https://openalex.org/W4404645275"],"related_works":[],"abstract_inverted_index":{"As":[0],"a":[1,10,36,64,116,121,140,176,214],"data":[2,54],"preprocessing":[3],"step,":[4],"clustering":[5,66],"high-dimensional":[6,42,75],"vector":[7,78,114,127],"streams":[8],"plays":[9],"critical":[11,190],"role":[12],"in":[13,21,27,44,115,220,232],"many":[14],"applications":[15],"such":[16,124],"as":[17],"recommendation,":[18],"community":[19],"detection":[20,26],"social":[22],"networks,":[23],"and":[24,60,74,185,193,200,223],"anomaly":[25],"large-scale":[28],"computer":[29],"networks.":[30],"In":[31],"this":[32,136],"work,":[33],"we":[34,97,174],"propose":[35],"scalable":[37],"framework,":[38],"Suffice,":[39],"to":[40,71,87,133,135,143,191,218],"cluster":[41,117,168,230,233],"vectors":[43,109,146],"streaming":[45,202],"environments":[46],"that":[47,68,104,125,147,179,209],"continuously":[48],"experience":[49],"three":[50],"fundamental":[51],"types":[52],"of":[53,77,91,152,160,170,227],"update":[55],"including":[56],"entry":[57],"values,":[58],"vectors,":[59,96],"dimensions.":[61],"Suffice":[62,210],"features":[63],"new":[65],"definition":[67,231],"is":[69,118,131],"native":[70],"the":[72,89,150,153,158,167,225],"dynamic":[73],"nature":[76],"streams.":[79],"Moreover,":[80],"it":[81,130],"incorporates":[82],"two":[83],"key":[84],"optimizations.":[85],"First,":[86],"minimize":[88],"frequency":[90],"pairwise":[92],"similarity":[93,163,188],"comparisons":[94,164],"between":[95],"design":[98,139],"an":[99],"adaptive":[100],"multiple":[101,107],"reference":[102,108,113,145,195],"strategy":[103],"dynamically":[105],"selects":[106],"per":[110],"cluster.":[111,137],"Each":[112],"associated":[119],"with":[120,213],"safe":[122,154],"region":[123],"any":[126],"falling":[128],"into":[129],"guaranteed":[132],"belong":[134],"We":[138],"reward":[141],"function":[142],"select":[144],"jointly":[148],"maximize":[149],"size":[151],"region,":[155],"thus":[156],"minimizing":[157],"chance":[159],"conducting":[161],"extra":[162],"when":[165],"determining":[166],"membership":[169],"incoming":[171],"vectors.":[172,196],"Second,":[173],"introduce":[175],"double-hash":[177],"structure":[178],"efficiently":[180],"supports":[181],"both":[182,198],"nearest":[183],"neighbor-based":[184,187],"furthest":[186],"searches,":[189],"selecting":[192],"searching":[194],"Using":[197],"real-world":[199],"synthetic":[201],"datasets,":[203],"our":[204,228],"comprehensive":[205],"experimental":[206],"studies":[207],"confirm":[208],"outperforms":[211],"baselines":[212],"speedup":[215],"from":[216],"18\u00d7":[217],"120\u00d7":[219],"run":[221],"time":[222],"demonstrate":[224],"superiority":[226],"proposed":[229],"quality.":[234]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-08T00:00:00"}