{"id":"https://openalex.org/W4292621762","doi":"https://doi.org/10.1145/3546157.3546158","title":"Clustering Faster and Better with Projected Data","display_name":"Clustering Faster and Better with Projected Data","publication_year":2022,"publication_date":"2022-05-27","ids":{"openalex":"https://openalex.org/W4292621762","doi":"https://doi.org/10.1145/3546157.3546158"},"language":"en","primary_location":{"id":"doi:10.1145/3546157.3546158","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546157.3546158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 6th International Conference on Information System 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/A5038757341","display_name":"Alibek Zhakubayev","orcid":"https://orcid.org/0000-0002-6386-7715"},"institutions":[{"id":"https://openalex.org/I157394403","display_name":"Baylor University","ror":"https://ror.org/005781934","country_code":"US","type":"education","lineage":["https://openalex.org/I157394403"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alibek Zhakubayev","raw_affiliation_strings":["Department of Computer Science, Baylor University, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Baylor University, United States","institution_ids":["https://openalex.org/I157394403"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013375154","display_name":"Greg Hamerly","orcid":"https://orcid.org/0000-0002-0360-1544"},"institutions":[{"id":"https://openalex.org/I157394403","display_name":"Baylor University","ror":"https://ror.org/005781934","country_code":"US","type":"education","lineage":["https://openalex.org/I157394403"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Greg Hamerly","raw_affiliation_strings":["Department of Computer Science, Baylor University, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Baylor University, United States","institution_ids":["https://openalex.org/I157394403"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038757341"],"corresponding_institution_ids":["https://openalex.org/I157394403"],"apc_list":null,"apc_paid":null,"fwci":0.5307,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70713396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9993000030517578,"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":0.9993000030517578,"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/T10057","display_name":"Face and Expression Recognition","score":0.9988999962806702,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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":0.9330626726150513},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.7454991936683655},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.7188756465911865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955840587615967},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.6592158079147339},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.6088972687721252},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.6003727912902832},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5718898773193359},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5687830448150635},{"id":"https://openalex.org/keywords/k-medians-clustering","display_name":"k-medians clustering","score":0.5446325540542603},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5218333601951599},{"id":"https://openalex.org/keywords/random-projection","display_name":"Random projection","score":0.5120657086372375},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.5014195442199707},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.43424010276794434},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.414175808429718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3339351713657379},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2880933880805969},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23211172223091125}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9330626726150513},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7454991936683655},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.7188756465911865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955840587615967},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.6592158079147339},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.6088972687721252},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.6003727912902832},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5718898773193359},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5687830448150635},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.5446325540542603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5218333601951599},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.5120657086372375},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.5014195442199707},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.43424010276794434},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.414175808429718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3339351713657379},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2880933880805969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23211172223091125},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3546157.3546158","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546157.3546158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 6th International Conference on Information System and Data Mining","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":9,"referenced_works":["https://openalex.org/W118481696","https://openalex.org/W1577871831","https://openalex.org/W2007339694","https://openalex.org/W2037757210","https://openalex.org/W2041836310","https://openalex.org/W2088658556","https://openalex.org/W2100060407","https://openalex.org/W2414895359","https://openalex.org/W2560674852"],"related_works":["https://openalex.org/W2389934482","https://openalex.org/W3176177124","https://openalex.org/W4241252752","https://openalex.org/W2356030476","https://openalex.org/W2590117803","https://openalex.org/W2185743328","https://openalex.org/W4310575853","https://openalex.org/W1491908038","https://openalex.org/W2567087402","https://openalex.org/W2046825742"],"abstract_inverted_index":{"The":[0],"K-means":[1,73],"clustering":[2,52,63,84,131],"algorithm":[3],"can":[4],"take":[5],"a":[6,20,50,54,89,132],"lot":[7],"of":[8,23,41,57],"time":[9,70,128],"to":[10,32,88,100,115],"converge,":[11],"especially":[12],"for":[13,92,130],"large":[14,21],"datasets":[15],"in":[16,53,64,77,135],"high":[17],"dimension":[18],"and":[19,80,108,134],"number":[22],"clusters.":[24],"By":[25],"applying":[26],"several":[27],"enhancements":[28],"it":[29,105],"is":[30,106],"possible":[31],"improve":[33],"the":[34,39,42,58,62,65,81,93,102,110,127],"performance":[35],"without":[36],"significantly":[37,125],"changing":[38],"quality":[40],"clustering.":[43],"In":[44,117],"this":[45,123],"paper":[46],"we":[47,113,120],"first":[48],"find":[49],"good":[51,90],"reduced-dimension":[55],"version":[56],"dataset,":[59],"before":[60],"fine-tuning":[61],"original":[66,94],"dimension.":[67],"This":[68],"saves":[69],"because":[71],"accelerated":[72],"algorithms":[74],"are":[75],"fastest":[76],"low":[78],"dimension,":[79,103],"initial":[82],"low-dimensional":[83],"bring":[85],"us":[86],"close":[87],"solution":[91],"data.":[95],"We":[96],"use":[97],"random":[98],"projection":[99],"reduce":[101],"as":[104],"fast":[107],"maintains":[109],"cluster":[111],"properties":[112],"want":[114],"preserve.":[116],"our":[118],"experiments,":[119],"see":[121],"that":[122],"approach":[124],"reduces":[126],"needed":[129],"dataset":[133],"most":[136],"cases":[137],"produces":[138],"better":[139],"results.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}