{"id":"https://openalex.org/W2748619008","doi":"https://doi.org/10.1073/pnas.2100482118","title":"Two provably consistent divide-and-conquer clustering algorithms for large networks","display_name":"Two provably consistent divide-and-conquer clustering algorithms for large networks","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W2748619008","doi":"https://doi.org/10.1073/pnas.2100482118","mag":"2748619008","pmid":"https://pubmed.ncbi.nlm.nih.gov/34716259","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/8612351"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.2100482118","doi":"https://doi.org/10.1073/pnas.2100482118","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.2100482118","pdf_url":null,"source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","erih-plus","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8612351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085153518","display_name":"Soumendu Sundar Mukherjee","orcid":"https://orcid.org/0000-0002-6716-9586","observed_orcids":["https://orcid.org/0000-0002-6716-9586"]},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Soumendu Sundar Mukherjee","raw_affiliation_strings":["Department of Statistics, University of California, Berkeley, CA 94720","Interdisciplinary Statistical Research Unit, Indian Statistical Institute, Kolkata 700108, India;","Interdisciplinary Statistical Research Unit, Indian Statistical Institute, Kolkata 700108, India; soumendu041@gmail.com bickel@stat.berkeley.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, Berkeley, CA 94720","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Interdisciplinary Statistical Research Unit, Indian Statistical Institute, Kolkata 700108, India;","institution_ids":["https://openalex.org/I6498739"]},{"raw_affiliation_string":"Interdisciplinary Statistical Research Unit, Indian Statistical Institute, Kolkata 700108, India; soumendu041@gmail.com bickel@stat.berkeley.edu","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065384967","display_name":"Purnamrita Sarkar","orcid":"https://orcid.org/0000-0002-6542-1215","observed_orcids":["https://orcid.org/0000-0002-6542-1215"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Purnamrita Sarkar","raw_affiliation_strings":["Department of Statistics and Data Sciences, University of Texas at Austin, Austin, TX 78705"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Sciences, University of Texas at Austin, Austin, TX 78705","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025311999","display_name":"Peter J. Bickel","orcid":"https://orcid.org/0000-0001-7480-662X","observed_orcids":["https://orcid.org/0000-0001-7480-662X"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter J. Bickel","raw_affiliation_strings":["Department of Statistics, University of California, Berkeley, CA 94720;","Department of Statistics, University of California, Berkeley, CA 94720; soumendu041@gmail.com bickel@stat.berkeley.edu"],"raw_orcid":"https://orcid.org/0000-0001-7480-662X","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, Berkeley, CA 94720;","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Statistics, University of California, Berkeley, CA 94720; soumendu041@gmail.com bickel@stat.berkeley.edu","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7597,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.65888104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"118","issue":"44","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9824000000953674,"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"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9824000000953674,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.014100000262260437,"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/T10136","display_name":"Statistical Methods and Inference","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/community-detection","display_name":"community detection","score":0.8349999785423279},{"id":"https://openalex.org/keywords/large-scale-networks","display_name":"large-scale networks","score":0.6890000104904175},{"id":"https://openalex.org/keywords/subgraph-selection","display_name":"subgraph selection","score":0.753000020980835},{"id":"https://openalex.org/keywords/consistency-proofs","display_name":"consistency proofs","score":0.5709999799728394},{"id":"https://openalex.org/keywords/parallelizable-algorithms","display_name":"parallelizable algorithms","score":0.5559999942779541},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.49900001287460327},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"spectral clustering","score":0.7289999723434448},{"id":"https://openalex.org/keywords/modularity-maximization","display_name":"modularity optimization","score":0.8040000200271606},{"id":"https://openalex.org/keywords/likelihood-based-methods","display_name":"likelihood methods","score":0.6850000023841858},{"id":"https://openalex.org/keywords/semidefinite-programming","display_name":"semidefinite programming","score":0.871999979019165}],"concepts":[{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.9219073057174683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7593348622322083},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7411662936210632},{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.7118690609931946},{"id":"https://openalex.org/C128243737","wikidata":"https://www.wikidata.org/wiki/Q5134414","display_name":"Clique percolation method","level":3,"score":0.6712489724159241},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5746005773544312},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.5255906581878662},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4462599754333496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4407179355621338},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3356602191925049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2536887228488922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24164193868637085},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1073/pnas.2100482118","doi":"https://doi.org/10.1073/pnas.2100482118","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.2100482118","pdf_url":null,"source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","erih-plus","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8612351","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8612351","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proc Natl Acad Sci U S A","raw_type":"Text"},{"id":"pmid:34716259","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34716259","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences of the United States of America","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:1708.05573","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.05573","pdf_url":"https://arxiv.org/pdf/1708.05573","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2748619008","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.05573.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1708.05573","doi":"https://doi.org/10.48550/arxiv.1708.05573","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.05573","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8612351","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8612351","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proc Natl Acad Sci U S A","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4318754190","display_name":"Collaborative Research: Inference for Network Models with Covariates: Leveraging Local Information for Statistically and Computationally Efficient Estimation of Global Parameters","funder_award_id":"1713083","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5483422842","display_name":"Collaborative Research: Inference for Network Models with Covariates: Leveraging Local Information for Statistically and Computationally Efficient Estimation of Global Parameters","funder_award_id":"1713082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2748619008.pdf","grobid_xml":"https://content.openalex.org/works/W2748619008.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W379337736","https://openalex.org/W934261879","https://openalex.org/W1566036427","https://openalex.org/W1605711022","https://openalex.org/W1626328221","https://openalex.org/W1710085869","https://openalex.org/W1791748083","https://openalex.org/W1803616914","https://openalex.org/W1855425795","https://openalex.org/W1930572491","https://openalex.org/W1963954507","https://openalex.org/W1967184357","https://openalex.org/W1973207991","https://openalex.org/W1981276685","https://openalex.org/W2000116444","https://openalex.org/W2003827790","https://openalex.org/W2012833704","https://openalex.org/W2064274783","https://openalex.org/W2066828202","https://openalex.org/W2073094091","https://openalex.org/W2095293504","https://openalex.org/W2102158416","https://openalex.org/W2102907934","https://openalex.org/W2107107106","https://openalex.org/W2111315907","https://openalex.org/W2114244473","https://openalex.org/W2119998616","https://openalex.org/W2121947440","https://openalex.org/W2144799688","https://openalex.org/W2152284345","https://openalex.org/W2155461593","https://openalex.org/W2157305458","https://openalex.org/W2162833336","https://openalex.org/W2165874743","https://openalex.org/W2169379894","https://openalex.org/W2222512263","https://openalex.org/W2232943036","https://openalex.org/W2342539172","https://openalex.org/W2408125176","https://openalex.org/W2536263232","https://openalex.org/W2597289420","https://openalex.org/W2604272474","https://openalex.org/W2766844003","https://openalex.org/W2768480272","https://openalex.org/W2890494455","https://openalex.org/W2904558712","https://openalex.org/W2962715745","https://openalex.org/W2963626317","https://openalex.org/W2963847248","https://openalex.org/W3015166416","https://openalex.org/W3100144903","https://openalex.org/W3104329805","https://openalex.org/W3142588439","https://openalex.org/W4238452917","https://openalex.org/W7208385477"],"related_works":["https://openalex.org/W2904558712","https://openalex.org/W4386376301","https://openalex.org/W4224913948","https://openalex.org/W2524039959","https://openalex.org/W7099508412","https://openalex.org/W2787309501","https://openalex.org/W6929405609","https://openalex.org/W1967937629","https://openalex.org/W2088193897","https://openalex.org/W1621117074"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"advance":[4],"divide-and-conquer":[5,97,136],"strategies":[6],"for":[7,103],"solving":[8],"the":[9,29,47,86,113,132,135],"community":[10],"detection":[11],"problem":[12],"in":[13,93,138],"networks.":[14,110],"We":[15,111],"propose":[16],"two":[17],"algorithms":[18,40,73,82,106,117],"that":[19,42],"perform":[20,124],"clustering":[21],"on":[22],"several":[23],"small":[24,94],"subgraphs":[25],"and":[26,66,85,123,127],"finally":[27],"patch":[28],"results":[30],"into":[31],"a":[32],"single":[33],"clustering.":[34],"The":[35],"main":[36],"advantage":[37],"of":[38,50,115,134],"these":[39,116],"is":[41],"they":[43],"significantly":[44],"bring":[45],"down":[46],"computational":[48],"cost":[49],"traditional":[51,81,105],"algorithms,":[52],"including":[53],"spectral":[54],"clustering,":[55],"semidefinite":[56],"programs,":[57],"modularity-based":[58],"methods,":[59,61],"likelihood-based":[60],"etc.,":[62],"without":[63],"losing":[64],"accuracy,":[65],"even":[67],"improving":[68],"accuracy":[69],"at":[70],"times.":[71],"These":[72],"are":[74,83,90],"also,":[75],"by":[76],"nature,":[77],"parallelizable.":[78],"Since":[79],"most":[80],"accurate,":[84],"corresponding":[87],"optimization":[88],"problems":[89],"much":[91],"simpler":[92],"problems,":[95],"our":[96],"methods":[98],"provide":[99],"an":[100],"omnibus":[101],"recipe":[102],"scaling":[104],"up":[107],"to":[108,130],"large":[109],"prove":[112],"consistency":[114],"under":[118],"various":[119,139],"subgraph":[120],"selection":[121],"procedures":[122],"extensive":[125],"simulations":[126],"real-data":[128],"analysis":[129],"understand":[131],"advantages":[133],"approach":[137],"settings.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-08-31T00:00:00"}