{"id":"https://openalex.org/W4378895511","doi":"https://doi.org/10.1145/3558481.3591318","title":"Brief Announcement: Streaming Balanced Clustering","display_name":"Brief Announcement: Streaming Balanced Clustering","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4378895511","doi":"https://doi.org/10.1145/3558481.3591318"},"language":"en","primary_location":{"id":"doi:10.1145/3558481.3591318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558481.3591318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures","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/A5047480720","display_name":"Hossein Esfandiari","orcid":"https://orcid.org/0000-0001-8130-6631"},"institutions":[{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hossein Esfandiari","raw_affiliation_strings":["Google Research, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Google Research, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075598023","display_name":"Vahab Mirrokni","orcid":"https://orcid.org/0000-0001-6705-5629"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahab Mirrokni","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062439923","display_name":"Peilin Zhong","orcid":"https://orcid.org/0009-0001-1136-9538"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peilin Zhong","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047480720"],"corresponding_institution_ids":["https://openalex.org/I4210113297"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04876369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987000226974487,"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":0.9987000226974487,"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/T10057","display_name":"Face and Expression Recognition","score":0.9984999895095825,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9961000084877014,"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":0.9080243706703186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.758296549320221},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5825865864753723},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5574378371238708},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.5463339686393738},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5359426736831665},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.5224648714065552},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5133072733879089},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4975278675556183},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4901965260505676},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48577311635017395},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.48464590311050415},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.47377729415893555},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3060620129108429},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1390782594680786},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0780947208404541},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.0654670000076294}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9080243706703186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758296549320221},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5825865864753723},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5574378371238708},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.5463339686393738},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5359426736831665},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.5224648714065552},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5133072733879089},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4975278675556183},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4901965260505676},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48577311635017395},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.48464590311050415},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.47377729415893555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3060620129108429},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1390782594680786},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0780947208404541},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.0654670000076294},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3558481.3591318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558481.3591318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures","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":22,"referenced_works":["https://openalex.org/W1623845008","https://openalex.org/W1977983731","https://openalex.org/W1981773323","https://openalex.org/W2045964207","https://openalex.org/W2049744118","https://openalex.org/W2091684877","https://openalex.org/W2094048240","https://openalex.org/W2117999038","https://openalex.org/W2125531986","https://openalex.org/W2171125141","https://openalex.org/W2260613758","https://openalex.org/W2262337340","https://openalex.org/W2264057010","https://openalex.org/W2279901945","https://openalex.org/W2547958265","https://openalex.org/W2593080689","https://openalex.org/W2609713339","https://openalex.org/W2964138263","https://openalex.org/W3001164300","https://openalex.org/W4247564011","https://openalex.org/W4313227433","https://openalex.org/W6840899164"],"related_works":["https://openalex.org/W2770806490","https://openalex.org/W2436677952","https://openalex.org/W2375148282","https://openalex.org/W2564198485","https://openalex.org/W3186815950","https://openalex.org/W2156499390","https://openalex.org/W3124860551","https://openalex.org/W2288470165","https://openalex.org/W2309230723","https://openalex.org/W2202413591"],"abstract_inverted_index":{"Clustering":[0],"of":[1,18,29,56,60,87],"data":[2,21],"points":[3],"in":[4,13,20,46],"metric":[5],"space":[6],"is":[7,63,98],"among":[8],"the":[9,52,57,85,88,90],"most":[10],"fundamental":[11],"problems":[12,45,62],"computer":[14],"science":[15],"with":[16,33],"plenty":[17],"applications":[19,31],"mining,":[22],"information":[23],"retrieval":[24],"and":[25,36,80,116],"machine":[26],"learning.":[27],"Many":[28],"these":[30,44],"deal":[32],"large":[34,47],"datasets,":[35],"hence":[37],"researchers":[38],"focused":[39],"on":[40],"designing":[41],"algorithms":[42],"for":[43,95,106],"scale":[48],"settings":[49],"such":[50],"as":[51],"streaming":[53,93,104],"setting.":[54],"One":[55],"sweet":[58],"versions":[59],"clustering":[61,65,97,108],"balanced":[64],"(or":[66],"more":[67],"generally":[68],"capacitated":[69,96,107],"clustering),":[70],"where":[71],"we":[72],"do":[73],"not":[74],"desire":[75],"to":[76],"have":[77],"some":[78],"giant":[79],"several":[81],"small":[82],"clusters.":[83],"Despite":[84],"importance":[86],"context,":[89],"best":[91],"known":[92],"algorithm":[94,105],"far":[99],"from":[100],"optimal.":[101],"The":[102],"state-of-the-art":[103],"gives":[109],"an":[110],"O(1)-approximate":[111],"solution,":[112],"requires":[113],"three":[114],"passes":[115],"only":[117],"handles":[118],"insertions":[119],"(Bateni":[120],"et":[121],"al.":[122],"NeurIPS'14).":[123]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}