{"id":"https://openalex.org/W7164745272","doi":"https://doi.org/10.1016/j.is.2026.102768","title":"Approximate hierarchical density-based clustering using graph-based search indexes","display_name":"Approximate hierarchical density-based clustering using graph-based search indexes","publication_year":2026,"publication_date":"2026-06-14","ids":{"openalex":"https://openalex.org/W7164745272","doi":"https://doi.org/10.1016/j.is.2026.102768"},"language":"en","primary_location":{"id":"doi:10.1016/j.is.2026.102768","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.is.2026.102768","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.is.2026.102768","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114390075","display_name":"Camilla Birch Okkels","orcid":"https://orcid.org/0009-0005-1904-4024"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Camilla Birch Okkels","raw_affiliation_strings":["IT University of Copenhagen, 2300, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0009-0005-1904-4024","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, 2300, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032188248","display_name":"Erik Thordsen","orcid":"https://orcid.org/0000-0003-1639-3534"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erik Thordsen","raw_affiliation_strings":["TU Dortmund University, Informatik, 44221, Dortmund Germany"],"raw_orcid":"https://orcid.org/0000-0003-1639-3534","affiliations":[{"raw_affiliation_string":"TU Dortmund University, Informatik, 44221, Dortmund Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072434673","display_name":"Martin Aum\u00fcller","orcid":"https://orcid.org/0000-0002-7212-6476"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Martin Aum\u00fcller","raw_affiliation_strings":["IT University of Copenhagen, 2300, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-7212-6476","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, 2300, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047196019","display_name":"Arthur Zimek","orcid":"https://orcid.org/0000-0001-7713-4208"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Arthur Zimek","raw_affiliation_strings":["University of Southern Denmark, IMADA, 5230, Odense Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7713-4208","affiliations":[{"raw_affiliation_string":"University of Southern Denmark, IMADA, 5230, Odense Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068514720","display_name":"Erich Schubert","orcid":"https://orcid.org/0000-0001-9143-4880"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Erich Schubert","raw_affiliation_strings":["TU Dortmund University, Informatik, 44221, Dortmund Germany"],"raw_orcid":"https://orcid.org/0000-0001-9143-4880","affiliations":[{"raw_affiliation_string":"TU Dortmund University, Informatik, 44221, Dortmund Germany","institution_ids":["https://openalex.org/I200332995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068514720","https://openalex.org/A5072434673"],"corresponding_institution_ids":["https://openalex.org/I200332995","https://openalex.org/I83467386"],"apc_list":{"value":2840,"currency":"USD","value_usd":2840},"apc_paid":{"value":2840,"currency":"USD","value_usd":2840},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73075287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"142","issue":null,"first_page":"102768","last_page":"102768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.39149999618530273,"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":0.39149999618530273,"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":0.32019999623298645,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.04280000180006027,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6545000076293945},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4648999869823456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/hierarchical-clustering-of-networks","display_name":"Hierarchical clustering of networks","score":0.39169999957084656},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.3310000002384186},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.329800009727478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223999738693237},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6545000076293945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5598999857902527},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4648999869823456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4641999900341034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C82261393","wikidata":"https://www.wikidata.org/wiki/Q17038699","display_name":"Hierarchical clustering of networks","level":5,"score":0.39169999957084656},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.2976999878883362},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.2784999907016754},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.272599995136261}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.is.2026.102768","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.is.2026.102768","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.is.2026.102768","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.is.2026.102768","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1965680834","https://openalex.org/W2049758109","https://openalex.org/W2055063781","https://openalex.org/W2120636855","https://openalex.org/W2180566385","https://openalex.org/W2532189199","https://openalex.org/W2592371352","https://openalex.org/W2740025111","https://openalex.org/W2740924709","https://openalex.org/W2923023146","https://openalex.org/W2963469388","https://openalex.org/W4407367173"],"related_works":[],"abstract_inverted_index":{"Current":[0],"exact":[1,96],"hierarchical":[2,18],"density-based":[3,19],"clustering":[4,24,122,127],"algorithms":[5,15,131],"for":[6,16,22,26,82],"high-dimensional":[7],"data":[8],"have":[9],"asymptotically":[10],"quadratic":[11],"complexity.":[12],"We":[13,33,86,105],"present":[14],"approximate":[17],"clustering,":[20],"namely":[21],"single-linkage":[23,126],"and":[25,42,70,98,121,128],"HDBSCAN,":[27,129],"with":[28],"empirically":[29],"near-linear":[30],"time":[31,120],"scalability.":[32],"explore":[34,106],"both":[35,66,125],"graph":[36,49,57,62],"index-based":[37],"incremental":[38],"nearest":[39],"neighbor":[40],"search":[41,84],"an":[43,77,99],"iterative":[44],"exploration":[45],"scheme":[46],"on":[47,113],"the":[48,52,55,67,90,107,110,114],"index":[50],"approximating":[51],"MST":[53],"of":[54,73,76,109,118,142],"reachability":[56],"similar":[58],"to":[59,92,139],"Kruskal.":[60],"As":[61],"index,":[63],"we":[64],"use":[65],"bottom":[68],"layer":[69],"a":[71,80],"combination":[72],"all":[74],"layers":[75],"HNSW":[78,111],"as":[79,95,149],"stand-in":[81],"connected":[83],"graphs.":[85],"provide":[87],"experiments":[88],"comparing":[89],"clusterings":[91,135],"baselines":[93,147],"such":[94,148],"implementation":[97],"algorithm":[100],"using":[101],"metric":[102],"tree-based":[103],"searchers.":[104],"impact":[108],"hyperparameters":[112],"performance":[115],"in":[116],"terms":[117],"running":[119],"quality.":[123],"For":[124],"our":[130],"yield":[132],"highly":[133],"accurate":[134],"while":[136],"being":[137],"up":[138],"two":[140],"orders":[141],"magnitude":[143],"faster":[144],"than":[145],"industry-standard":[146],"scikit-learn\u2019s":[150],"hdbscan":[151],".":[152]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-15T00:00:00"}