{"id":"https://openalex.org/W2616975746","doi":"https://doi.org/10.1109/fuzz-ieee.2017.8015720","title":"SHCoClust, a scalable similarity-based hierarchical co-clustering method and its application to textual collections","display_name":"SHCoClust, a scalable similarity-based hierarchical co-clustering method and its application to textual collections","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2616975746","doi":"https://doi.org/10.1109/fuzz-ieee.2017.8015720","mag":"2616975746"},"language":"en","primary_location":{"id":"doi:10.1109/fuzz-ieee.2017.8015720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz-ieee.2017.8015720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-02053700","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100352822","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0002-9731-1723"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["Universit\u00e9 de Lyon Lyon 2, Bron Cedex, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lyon Lyon 2, Bron Cedex, France","institution_ids":["https://openalex.org/I100532134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041442665","display_name":"Julien Ah-Pine","orcid":"https://orcid.org/0000-0001-6898-3961"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Ah-Pine","raw_affiliation_strings":["Universit\u00e9 de Lyon Lyon 2, Bron Cedex, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lyon Lyon 2, Bron Cedex, France","institution_ids":["https://openalex.org/I100532134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080624394","display_name":"J\u00e9r\u00f4me Darmont","orcid":"https://orcid.org/0000-0003-1491-384X"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jerome Darmont","raw_affiliation_strings":["Universit\u00e9 de Lyon Lyon 2, Bron Cedex, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lyon Lyon 2, Bron Cedex, France","institution_ids":["https://openalex.org/I100532134"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100352822"],"corresponding_institution_ids":["https://openalex.org/I100532134"],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62667931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","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":0.9994999766349792,"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":0.9994999766349792,"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":0.9966999888420105,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9948999881744385,"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":0.795946478843689},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6774418950080872},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6207830309867859},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.567514181137085},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5540784001350403},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5496460199356079},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5416342616081238},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5383490324020386},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5373638272285461},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.5156242251396179},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4978470802307129},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46736809611320496},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4603545069694519},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.45987385511398315},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4321445822715759},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3617863655090332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3598967492580414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22787514328956604},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1647135615348816}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.795946478843689},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6774418950080872},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6207830309867859},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.567514181137085},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5540784001350403},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5496460199356079},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5416342616081238},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5383490324020386},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5373638272285461},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.5156242251396179},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4978470802307129},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46736809611320496},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4603545069694519},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.45987385511398315},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4321445822715759},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3617863655090332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3598967492580414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22787514328956604},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1647135615348816},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/fuzz-ieee.2017.8015720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz-ieee.2017.8015720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01504986v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01504986","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2017","raw_type":"Preprints, Working Papers, ..."},{"id":"pmh:oai:HAL:hal-02053700v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02053700","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.fuzzieee2017.org/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02053700v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02053700","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.fuzzieee2017.org/","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1613448136","https://openalex.org/W2066965880","https://openalex.org/W2090257125","https://openalex.org/W2133576408","https://openalex.org/W2144544802","https://openalex.org/W2149684865","https://openalex.org/W2153233077","https://openalex.org/W2504829889","https://openalex.org/W2521429073","https://openalex.org/W4235169531","https://openalex.org/W4242399520","https://openalex.org/W6682304300"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2622412490","https://openalex.org/W3140018618","https://openalex.org/W2590117803","https://openalex.org/W2393707058","https://openalex.org/W2414630753","https://openalex.org/W2202413591","https://openalex.org/W2389934482","https://openalex.org/W2388628913","https://openalex.org/W2152187121"],"abstract_inverted_index":{"In":[0,150],"comparison":[1],"with":[2,132,152],"flat":[3],"clustering":[4,10,22,148,172],"methods,":[5],"such":[6],"as":[7],"K-means,":[8],"hierarchical":[9,21,64,147],"and":[11,32,40,48,94,110,117,134,162,187],"co-clustering":[12,33,65],"methods":[13],"are":[14,113,193],"more":[15],"advantageous,":[16],"for":[17,115,118],"the":[18,27,69,96,125,145,154,171],"reason":[19],"that":[20,107,141],"is":[23,75,167],"capable":[24,168],"to":[25,77,82,127,169,183],"reveal":[26],"internal":[28],"connections":[29],"of":[30,37,85,98],"clusters,":[31],"can":[34,100],"yield":[35],"clusters":[36],"data":[38],"instances":[39],"features.":[41],"Interested":[42],"in":[43,46,49,55,72],"organizing":[44],"co-clusters":[45],"hierarchy":[47],"discovering":[50],"cluster":[51],"hierarchies":[52],"inside":[53],"co-clusters,":[54],"this":[56],"paper,":[57],"we":[58],"propose":[59],"SHCoClust,":[60],"a":[61],"scalable":[62],"similarity-based":[63],"method.":[66],"Except":[67],"possessing":[68],"above-mentioned":[70],"advantages":[71],"unison,":[73],"SHCoClust":[74,99,122,142,166],"able":[76],"employ":[78],"kernel":[79,161],"functions,":[80],"thanks":[81],"its":[83,176],"utilization":[84],"inner":[86],"product.":[87],"Furthermore,":[88],"having":[89],"all":[90],"similarities":[91],"between":[92],"0":[93],"1,":[95],"input":[97,155,177],"be":[101],"sparsified":[102],"by":[103,159,163],"threshold":[104],"values,":[105],"so":[106],"less":[108,111],"memory":[109,191],"time":[112,185],"required":[114],"storage":[116],"computation.":[119],"This":[120],"grants":[121],"scalability,":[123],"i.e,":[124],"ability":[126],"process":[128],"relatively":[129],"large":[130],"datasets":[131],"reduced":[133],"limited":[135],"computing":[136],"resources.":[137],"Our":[138],"experiments":[139],"demonstrate":[140],"significantly":[143],"outperforms":[144],"conventional":[146],"methods.":[149],"addition,":[151],"sparsifying":[153],"similarity":[156],"matrices":[157],"obtained":[158],"linear":[160],"Gaussian":[164],"kernel,":[165],"guarantee":[170],"quality,":[173],"even":[174],"when":[175],"being":[178],"largely":[179],"sparsified.":[180],"Consequently,":[181],"up":[182],"86%":[184],"gain":[186,192],"on":[188],"average":[189],"75%":[190],"achieved.":[194]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}