{"id":"https://openalex.org/W2022902860","doi":"https://doi.org/10.1145/1007568.1007621","title":"Incremental and effective data summarization for dynamic hierarchical clustering","display_name":"Incremental and effective data summarization for dynamic hierarchical clustering","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2022902860","doi":"https://doi.org/10.1145/1007568.1007621","mag":"2022902860"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","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/A5085369929","display_name":"Samer Nassar","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Samer Nassar","raw_affiliation_strings":["University of Alberta, Edmonton, Alberta, Canada","University of Alberta, Edmonton, Alberta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021763337","display_name":"J\u00f6rg Sander","orcid":"https://orcid.org/0000-0003-4068-7268"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Sander","raw_affiliation_strings":["University of Alberta, Edmonton, Alberta, Canada","University of Alberta, Edmonton, Alberta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111679224","display_name":"Corrine Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Corrine Cheng","raw_affiliation_strings":["University of Alberta, Edmonton, Alberta, Canada","University of Alberta, Edmonton, Alberta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta., Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4408,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.92532162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"467","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"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":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991000294685364,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9187357425689697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115831613540649},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7848647832870483},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7715005874633789},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6450330018997192},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6274301409721375},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.42146530747413635},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3624245226383209},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.26719021797180176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.20765936374664307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18391287326812744}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9187357425689697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115831613540649},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7848647832870483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7715005874633789},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6450330018997192},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6274301409721375},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.42146530747413635},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3624245226383209},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.26719021797180176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.20765936374664307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18391287326812744}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1007568.1007621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.5984","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.5984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/sigmodpods04/sigmod/pdf/R-459.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.4958","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.4958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~joerg/papers/SIGMOD-04-final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1489108128","https://openalex.org/W1530595269","https://openalex.org/W1578711506","https://openalex.org/W1673310716","https://openalex.org/W1949687736","https://openalex.org/W2045948812","https://openalex.org/W2070412788","https://openalex.org/W2080068757","https://openalex.org/W2095897464","https://openalex.org/W2110449999","https://openalex.org/W2117544284","https://openalex.org/W2120636855","https://openalex.org/W2127218421","https://openalex.org/W2158462786","https://openalex.org/W2160642098","https://openalex.org/W2169344281","https://openalex.org/W2169581671","https://openalex.org/W2170936641","https://openalex.org/W2171852577","https://openalex.org/W2271689365","https://openalex.org/W2978337448","https://openalex.org/W4247105055"],"related_works":["https://openalex.org/W3168768270","https://openalex.org/W3192757256","https://openalex.org/W1559971515","https://openalex.org/W4200404937","https://openalex.org/W4310575853","https://openalex.org/W4229003453","https://openalex.org/W4386117929","https://openalex.org/W3197105638","https://openalex.org/W2034053407","https://openalex.org/W4226410418"],"abstract_inverted_index":{"Mining":[0],"informative":[1],"patterns":[2,86],"from":[3],"very":[4,23],"large,":[5],"dynamically":[6,45],"changing":[7,54,98],"databases":[8,26,44],"poses":[9],"numerous":[10],"interesting":[11],"challenges.":[12],"Data":[13],"summarizations":[14],"(e.g.,":[15],"data":[16,56,67,85,110,116,138,144,153,162,180,185,191,216],"bubbles)":[17],"have":[18],"been":[19],"proposed":[20],"to":[21,48,73,108,142],"compress":[22,149],"large":[24,96],"static":[25],"into":[27],"representative":[28],"points":[29,154],"suitable":[30],"for":[31,95,136],"subsequent":[32],"effective":[33,203],"hierarchical":[34,120],"cluster":[35],"analysis.":[36],"In":[37,100,130],"many":[38],"real":[39],"world":[40],"applications,":[41],"however,":[42],"the":[43,55,66,70,75,78,83,178,190,212,215],"change":[46],"due":[47],"frequent":[49],"insertions":[50,91,157,198],"and":[51,58,69,81,90,158,169,199,201],"deletions,":[52,200],"possibly":[53],"distribution":[57],"clustering":[59,71,79,121],"structure":[60,80],"over":[61],"time.":[62,129],"Completely":[63],"reapplying":[64],"both":[65],"summarization":[68,186],"algorithm":[72],"detect":[74],"changes":[76],"in":[77,128,204,207],"update":[82],"uncovered":[84],"following":[87],"such":[88],"deletions":[89],"is":[92,122,140],"prohibitively":[93],"expensive":[94],"fast":[97],"databases.":[99],"this":[101],"paper,":[102],"we":[103],"propose":[104],"a":[105,118,133,194],"new":[106],"scheme":[107],"maintain":[109],"bubbles":[111,139,145,163,181,192],"incrementally.":[112],"By":[113],"using":[114,166],"incremental":[115,137,179],"bubbles,":[117],"high-quality":[119],"quickly":[123],"available":[124],"at":[125],"any":[126],"point":[127],"our":[131],"scheme,":[132],"quality":[134,213],"measure":[135],"used":[141],"identify":[143],"that":[146,177],"do":[147],"not":[148],"well":[150],"their":[151],"underlying":[152],"after":[155,193],"certain":[156,195],"deletions.":[159],"Only":[160],"these":[161],"are":[164,202],"re-built":[165],"efficient":[167],"split":[168],"merge":[170],"operations.":[171],"An":[172],"extensive":[173],"experimental":[174],"evaluation":[175],"shows":[176],"provide":[182],"significantly":[183],"faster":[184],"than":[187],"completely":[188],"re-building":[189],"number":[196],"of":[197,214],"preserving":[205],"(and":[206],"some":[208],"cases":[209],"even":[210],"improving)":[211],"summarization.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}