{"id":"https://openalex.org/W2007228933","doi":"https://doi.org/10.1109/tkde.2002.1000339","title":"Effect of data skewness and workload balance in parallel data mining","display_name":"Effect of data skewness and workload balance in parallel data mining","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2007228933","doi":"https://doi.org/10.1109/tkde.2002.1000339","mag":"2007228933"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2002.1000339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2002.1000339","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5108756735","display_name":"David W. Cheung","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"D.W. Cheung","raw_affiliation_strings":["Department of Computer and Information Systens, University of Hong Kong, Hong Kong, China","dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Systens, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063420989","display_name":"S.D. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"S.D. Lee","raw_affiliation_strings":["Department of Computer and Information Systens, University of Hong Kong, Hong Kong, China","dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Systens, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102056591","display_name":"Yongqiao Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yongqiao Xiao","raw_affiliation_strings":["Department of Computer and Information Systens, University of Hong Kong, Hong Kong, China","dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Systens, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108756735"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":6.9538,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96648255,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":"3","first_page":"498","last_page":"514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9914000034332275,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/skewness","display_name":"Skewness","score":0.8027386665344238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622464299201965},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.5816403031349182},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.5560612678527832},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5353306531906128},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5350134968757629},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5304507613182068},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.497146874666214},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4873691201210022},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41215163469314575},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35102468729019165},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.27254289388656616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15024808049201965},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11893299221992493}],"concepts":[{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.8027386665344238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622464299201965},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.5816403031349182},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.5560612678527832},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5353306531906128},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5350134968757629},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5304507613182068},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.497146874666214},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4873691201210022},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41215163469314575},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35102468729019165},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27254289388656616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15024808049201965},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11893299221992493},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tkde.2002.1000339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2002.1000339","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.15.5568","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.5568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csis.hku.hk/~sdlee/publications/TKDE02.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.2321","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.2321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.hku.hk/~dcheung/publication/tkde2002.pdf","raw_type":"text"},{"id":"pmh:oai:hub.hku.hk:10722/43659","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/43659","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W20184837","https://openalex.org/W1484413656","https://openalex.org/W1506285740","https://openalex.org/W1520890006","https://openalex.org/W1578959085","https://openalex.org/W1597161471","https://openalex.org/W1597561788","https://openalex.org/W1641039719","https://openalex.org/W1906561224","https://openalex.org/W1948199107","https://openalex.org/W2000473687","https://openalex.org/W2017394090","https://openalex.org/W2030969394","https://openalex.org/W2032519169","https://openalex.org/W2037965136","https://openalex.org/W2093456341","https://openalex.org/W2099111195","https://openalex.org/W2110039140","https://openalex.org/W2114624736","https://openalex.org/W2137860515","https://openalex.org/W2146411541","https://openalex.org/W2165372900","https://openalex.org/W2166559705","https://openalex.org/W2478708596","https://openalex.org/W2795859997","https://openalex.org/W2997167919","https://openalex.org/W2999729612","https://openalex.org/W4213251304","https://openalex.org/W4248966671","https://openalex.org/W4285719527","https://openalex.org/W6600858232","https://openalex.org/W6628750762","https://openalex.org/W6634775095","https://openalex.org/W6635733350"],"related_works":["https://openalex.org/W2189529952","https://openalex.org/W3122032734","https://openalex.org/W28389960","https://openalex.org/W3144675622","https://openalex.org/W3124374489","https://openalex.org/W4390063540","https://openalex.org/W3080076373","https://openalex.org/W2549038846","https://openalex.org/W4281381431","https://openalex.org/W1906561224"],"abstract_inverted_index":{"To":[0],"mine":[1,217],"association":[2,44,218],"rules":[3,45,219],"efficiently,":[4],"we":[5,37,157,215],"have":[6,158,170,176],"developed":[7,159],"a":[8,15,62,67,79,163,197,221],"new":[9],"parallel":[10,18,68,81],"mining":[11,42],"algorithm":[12,71,82],"FPM":[13,28,50,94,213],"on":[14,128],"distributed":[16,41,107],"share-nothing":[17],"system":[19],"in":[20,66,189],"which":[21,36],"data":[22,118,121],"are":[23,114,130,138,147,193],"partitioned":[24],"across":[25],"the":[26,33,84,98,143,153,167,191,201],"processors.":[27],"is":[29,95],"an":[30],"enhancement":[31],"of":[32,43,54,93,100,155],"FDM":[34,58],"algorithm,":[35],"previously":[38],"proposed":[39,131],"for":[40,83,132],"(Cheung":[46],"et":[47],"al.,":[48],"1996).":[49],"requires":[51],"fewer":[52],"rounds":[53],"message":[55],"exchanges":[56],"than":[57,196],"and,":[59],"hence,":[60],"has":[61,72],"better":[63,195],"response":[64],"time":[65],"environment.":[69],"The":[70,91,111,136],"been":[73],"experimentally":[74],"found":[75],"to":[76,97,116,151,161],"outperform":[77],"CD,":[78],"representative":[80],"same":[85],"goal":[86],"(Agrawal":[87],"and":[88,108,123,145,173,212],"Srikant,":[89],"1994).":[90],"efficiency":[92,154],"attributed":[96],"incorporation":[99],"two":[101,112,117,134],"powerful":[102],"candidate":[103],"sets":[104],"pruning":[105],"techniques:":[106],"global":[109],"prunings.":[110],"techniques":[113],"sensitive":[115],"distribution":[119],"characteristics,":[120],"skewness,":[122],"workload":[124],"balance.":[125],"Metrics":[126],"based":[127],"entropy":[129],"these":[133,185],"characteristics.":[135],"prunings":[137],"very":[139,187],"effective":[140],"when":[141],"both":[142],"skewness":[144],"balance":[146,172],"high.":[148],"In":[149],"order":[150],"increase":[152],"FPM,":[156],"methods":[160],"partition":[162],"database":[164,222],"so":[165],"that":[166,179],"resulting":[168],"partitions":[169],"high":[171],"skewness.":[174],"Experiments":[175],"shown":[177],"empirically":[178],"our":[180,209],"partitioning":[181,202,210],"algorithms":[182,203,211],"can":[183,216],"achieve":[184],"aims":[186],"well,":[188],"particular,":[190],"results":[192],"consistently":[194],"random":[198],"partitioning.":[199],"Moreover,":[200],"incur":[204],"little":[205],"overhead.":[206],"So,":[207],"using":[208],"together,":[214],"from":[220],"efficiently.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}