{"id":"https://openalex.org/W2597328883","doi":"https://doi.org/10.1109/tkde.2017.2681669","title":"Sparse Poisson Latent Block Model for Document Clustering","display_name":"Sparse Poisson Latent Block Model for Document Clustering","publication_year":2017,"publication_date":"2017-03-14","ids":{"openalex":"https://openalex.org/W2597328883","doi":"https://doi.org/10.1109/tkde.2017.2681669","mag":"2597328883"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2017.2681669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2681669","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/A5061716740","display_name":"Melissa Ailem","orcid":null},"institutions":[{"id":"https://openalex.org/I110736937","display_name":"D\u00e9l\u00e9gation Paris 5","ror":"https://ror.org/02e0y6e06","country_code":"FR","type":"government","lineage":["https://openalex.org/I110736937","https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4403386760","display_name":"Laboratoire Informatique Paris Descartes","ror":"https://ror.org/04s80ef73","country_code":"FR","type":"facility","lineage":["https://openalex.org/I204730241","https://openalex.org/I4403386760"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Melissa Ailem","raw_affiliation_strings":["LIPADE, University of Paris Descartes, France"],"affiliations":[{"raw_affiliation_string":"LIPADE, University of Paris Descartes, France","institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241","https://openalex.org/I4403386760"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003511531","display_name":"Fran\u00e7ois Role","orcid":null},"institutions":[{"id":"https://openalex.org/I110736937","display_name":"D\u00e9l\u00e9gation Paris 5","ror":"https://ror.org/02e0y6e06","country_code":"FR","type":"government","lineage":["https://openalex.org/I110736937","https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4403386760","display_name":"Laboratoire Informatique Paris Descartes","ror":"https://ror.org/04s80ef73","country_code":"FR","type":"facility","lineage":["https://openalex.org/I204730241","https://openalex.org/I4403386760"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Francois Role","raw_affiliation_strings":["LIPADE, University of Paris Descartes, France"],"affiliations":[{"raw_affiliation_string":"LIPADE, University of Paris Descartes, France","institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241","https://openalex.org/I4403386760"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007054746","display_name":"Mohamed Nadif","orcid":"https://orcid.org/0000-0002-0007-3950"},"institutions":[{"id":"https://openalex.org/I110736937","display_name":"D\u00e9l\u00e9gation Paris 5","ror":"https://ror.org/02e0y6e06","country_code":"FR","type":"government","lineage":["https://openalex.org/I110736937","https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4403386760","display_name":"Laboratoire Informatique Paris Descartes","ror":"https://ror.org/04s80ef73","country_code":"FR","type":"facility","lineage":["https://openalex.org/I204730241","https://openalex.org/I4403386760"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed Nadif","raw_affiliation_strings":["LIPADE, University of Paris Descartes, France"],"affiliations":[{"raw_affiliation_string":"LIPADE, University of Paris Descartes, France","institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241","https://openalex.org/I4403386760"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061716740"],"corresponding_institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241","https://openalex.org/I4403386760"],"apc_list":null,"apc_paid":null,"fwci":3.7418,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.94496804,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":"7","first_page":"1563","last_page":"1576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","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/T11901","display_name":"Bayesian Methods and Mixture Models","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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9860000014305115,"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":0.8248735070228577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7684133052825928},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5538062453269958},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.48645707964897156},{"id":"https://openalex.org/keywords/biclustering","display_name":"Biclustering","score":0.4683363437652588},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.45554935932159424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4141797423362732},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4124407172203064},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3924218714237213},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3796202540397644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.365444540977478},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.3172667622566223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1851804256439209},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08497509360313416},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07638728618621826}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8248735070228577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684133052825928},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5538062453269958},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.48645707964897156},{"id":"https://openalex.org/C144817290","wikidata":"https://www.wikidata.org/wiki/Q2976575","display_name":"Biclustering","level":5,"score":0.4683363437652588},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.45554935932159424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4141797423362732},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4124407172203064},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3924218714237213},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3796202540397644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365444540977478},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3172667622566223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1851804256439209},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08497509360313416},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07638728618621826},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2017.2681669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2681669","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308350","display_name":"American Academy of Pediatrics","ror":"https://ror.org/0512xad50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W93955028","https://openalex.org/W113396932","https://openalex.org/W658295343","https://openalex.org/W1488382947","https://openalex.org/W1493217831","https://openalex.org/W1790954942","https://openalex.org/W1981081578","https://openalex.org/W1981472895","https://openalex.org/W1984007049","https://openalex.org/W1998785512","https://openalex.org/W2010052339","https://openalex.org/W2011301426","https://openalex.org/W2019564823","https://openalex.org/W2026505375","https://openalex.org/W2043545458","https://openalex.org/W2049633694","https://openalex.org/W2059279601","https://openalex.org/W2064498790","https://openalex.org/W2071316194","https://openalex.org/W2080295262","https://openalex.org/W2083001254","https://openalex.org/W2109202835","https://openalex.org/W2133149215","https://openalex.org/W2133576408","https://openalex.org/W2144544802","https://openalex.org/W2149521737","https://openalex.org/W2180590172","https://openalex.org/W2325227998","https://openalex.org/W2406461395","https://openalex.org/W2552406463","https://openalex.org/W4242399520","https://openalex.org/W4244030505","https://openalex.org/W4245155814","https://openalex.org/W4255387915","https://openalex.org/W4285719527","https://openalex.org/W6621984194","https://openalex.org/W6629329278","https://openalex.org/W7037416921"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W2171610853","https://openalex.org/W3144143113","https://openalex.org/W3120229345","https://openalex.org/W3022637481","https://openalex.org/W2491448268","https://openalex.org/W2394117789","https://openalex.org/W2160785859","https://openalex.org/W2390610678","https://openalex.org/W2394193399"],"abstract_inverted_index":{"Over":[0],"the":[1,8,58,68,105,137,140,164,172],"last":[2],"decades,":[3],"several":[4],"studies":[5],"have":[6],"demonstrated":[7],"importance":[9],"of":[10,16,83,139,146,176],"co-clustering":[11,27,53],"to":[12,21,108,119,136,186],"simultaneously":[13],"produce":[14],"groups":[15],"objects":[17],"and":[18,149],"features.":[19],"Even":[20],"obtain":[22],"object":[23],"clusters":[24],"only,":[25],"using":[26],"is":[28,65,89,95],"often":[29],"more":[30],"effective":[31],"than":[32],"one-way":[33],"clustering,":[34],"especially":[35],"when":[36],"considering":[37],"sparse":[38],"high":[39],"dimensional":[40],"data.":[41,55,141],"In":[42],"this":[43],"paper,":[44],"we":[45],"present":[46],"a":[47,90,115],"novel":[48],"generative":[49],"mixture":[50],"model":[51,93],"for":[52,74],"such":[54,77],"This":[56],"model,":[57],"Sparse":[59],"Poisson":[60,69],"Latent":[61],"Block":[62],"Model":[63],"(SPLBM),":[64],"based":[66,155],"on":[67,143,156],"distribution,":[70],"which":[71,94,180],"arises":[72],"naturally":[73],"contingency":[75],"tables,":[76],"as":[78,123],"document-term":[79],"matrices.":[80],"The":[81],"advantages":[82],"SPLBM":[84,157],"are":[85,184],"two-fold.":[86],"First,":[87],"it":[88,100,127],"rigorous":[91],"statistical":[92],"also":[96,128],"very":[97],"parsimonious.":[98],"Second,":[99],"has":[101],"been":[102],"designed":[103],"from":[104],"ground":[106],"up":[107],"deal":[109],"with":[110],"data":[111],"sparsity":[112,138],"problems.":[113],"As":[114],"consequence,":[116],"in":[117,170],"addition":[118],"seeking":[120],"homogeneous":[121,131],"blocks,":[122],"other":[124,181],"available":[125],"algorithms,":[126],"filters":[129],"out":[130],"but":[132],"noisy":[133],"ones":[134],"due":[135],"Experiments":[142],"various":[144],"datasets":[145,179],"different":[147],"size":[148],"structure":[150,175],"show":[151],"that":[152],"an":[153],"algorithm":[154,166],"clearly":[158],"outperforms":[159],"state-of-the-art":[160],"algorithms.":[161],"Most":[162],"notably,":[163],"SPLBM-based":[165],"presented":[167],"here":[168],"succeeds":[169],"retrieving":[171],"natural":[173],"cluster":[174],"difficult,":[177],"unbalanced":[178],"known":[182],"algorithms":[183],"unable":[185],"handle":[187],"effectively.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}