{"id":"https://openalex.org/W4301776409","doi":"https://doi.org/10.1145/2736277.2741111","title":"Parallel Streaming Signature EM-tree","display_name":"Parallel Streaming Signature EM-tree","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W4301776409","doi":"https://doi.org/10.1145/2736277.2741111"},"language":"en","primary_location":{"id":"doi:10.1145/2736277.2741111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1505.05613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010759879","display_name":"Christopher M. De Vries","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124905","display_name":"Climate Analytics","ror":"https://ror.org/02yr08r26","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210124905"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christopher Michael De Vries","raw_affiliation_strings":["Game Analytics ApS, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Game Analytics ApS, Berlin, Germany","institution_ids":["https://openalex.org/I4210124905"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054450193","display_name":"Lance De Vine","orcid":"https://orcid.org/0000-0002-3728-7397"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lance De Vine","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045420626","display_name":"Shlomo Geva","orcid":"https://orcid.org/0000-0003-1340-2802"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shlomo Geva","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015158048","display_name":"Richi Nayak","orcid":"https://orcid.org/0000-0002-9954-0159"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richi Nayak","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1825,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91047654,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9983000159263611,"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":0.9983000159263611,"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/T11106","display_name":"Data Management and Algorithms","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8521888852119446},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7470593452453613},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6083561778068542},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.5867046117782593},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5441731810569763},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5068779587745667},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4821878969669342},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.43502235412597656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2222728431224823},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22080907225608826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2035330832004547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521888852119446},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7470593452453613},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6083561778068542},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.5867046117782593},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5441731810569763},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5068779587745667},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4821878969669342},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.43502235412597656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2222728431224823},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22080907225608826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2035330832004547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2736277.2741111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1505.05613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1505.05613","pdf_url":"https://arxiv.org/pdf/1505.05613","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1505.05613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1505.05613","pdf_url":"https://arxiv.org/pdf/1505.05613","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W32360141","https://openalex.org/W94637519","https://openalex.org/W153411086","https://openalex.org/W188912188","https://openalex.org/W299870200","https://openalex.org/W1554394657","https://openalex.org/W1634005169","https://openalex.org/W1685426458","https://openalex.org/W1738373647","https://openalex.org/W1870428314","https://openalex.org/W1966979133","https://openalex.org/W2012833704","https://openalex.org/W2016550647","https://openalex.org/W2032475142","https://openalex.org/W2036295879","https://openalex.org/W2036477303","https://openalex.org/W2041565863","https://openalex.org/W2062723323","https://openalex.org/W2065347041","https://openalex.org/W2073459066","https://openalex.org/W2076784111","https://openalex.org/W2089497633","https://openalex.org/W2100155384","https://openalex.org/W2105406322","https://openalex.org/W2108399535","https://openalex.org/W2150102617","https://openalex.org/W2165932491","https://openalex.org/W2167853719","https://openalex.org/W2190924945","https://openalex.org/W2232707661","https://openalex.org/W2538649358","https://openalex.org/W2882319491","https://openalex.org/W2950136222","https://openalex.org/W2979473749","https://openalex.org/W3145543370","https://openalex.org/W4213009331","https://openalex.org/W4230940751","https://openalex.org/W4231029117","https://openalex.org/W4255153203","https://openalex.org/W4301383669","https://openalex.org/W6607608502"],"related_works":["https://openalex.org/W2066858118","https://openalex.org/W3011699130","https://openalex.org/W2134017072","https://openalex.org/W1976914335","https://openalex.org/W2915208987","https://openalex.org/W2152256925","https://openalex.org/W1940452713","https://openalex.org/W2058150833","https://openalex.org/W2005567565","https://openalex.org/W2806040249"],"abstract_inverted_index":{"The":[0,109],"proliferation":[1],"of":[2,9,13,15,26,28,33,35,61,84,106,123,145,184,188],"the":[3,82,103,114,128,143,182,186],"web":[4,29,71],"presents":[5],"an":[6,157],"unsolved":[7],"problem":[8,183],"automatically":[10],"analyzing":[11],"billions":[12],"pages":[14,30,72],"natural":[16],"language.":[17],"We":[18],"introduce":[19],"a":[20,41,99],"scalable":[21],"algorithm":[22,112],"that":[23,101],"clusters":[24,126,155,189],"hundreds":[25,32],"millions":[27],"into":[31,76],"thousands":[34],"clusters.":[36,80,108],"It":[37,52],"does":[38],"this":[39],"on":[40],"single":[42],"mid-range":[43],"machine":[44],"using":[45,167],"efficient":[46],"algorithms":[47],"and":[48,64,68,73,119,173,195],"compressed":[49],"document":[50],"representations.":[51],"is":[53,134,193],"applied":[54],"to":[55,78],"two":[56,164],"web-scale":[57],"crawls":[58],"covering":[59],"tens":[60],"terabytes.":[62],"ClueWeb09":[63],"ClueWeb12":[65],"contain":[66],"500":[67],"733":[69],"million":[70],"were":[74],"clustered":[75,98],"500,000":[77],"700,000":[79],"To":[81],"best":[83],"our":[85],"knowledge,":[86],"such":[87],"fine":[88],"grained":[89,132],"clustering":[90,118,133,138],"has":[91],"not":[92],"been":[93],"previously":[94],"demonstrated.":[95],"Previous":[96],"approaches":[97],"sample":[100],"limits":[102],"maximum":[104],"number":[105,144],"discoverable":[107],"proposed":[110],"EM-tree":[111],"uses":[113],"entire":[115],"collection":[116,151],"in":[117,139],"produces":[120],"several":[121],"orders":[122],"magnitude":[124],"more":[125],"than":[127],"existing":[129],"algorithms.":[130],"Fine":[131],"necessary":[135],"for":[136,176],"meaningful":[137],"massive":[140],"collections":[141],"where":[142,190],"distinct":[146],"topics":[147],"grows":[148],"linearly":[149],"with":[150,163],"size.":[152],"These":[153,179],"fine-grained":[154],"show":[156],"improved":[158],"cluster":[159],"quality":[160,187],"when":[161],"assessed":[162],"novel":[165],"evaluations":[166,180],"ad":[168],"hoc":[169],"search":[170],"relevance":[171],"judgments":[172],"spam":[174],"classifications":[175],"external":[177],"validation.":[178],"solve":[181],"assessing":[185],"categorical":[191],"labeling":[192],"unavailable":[194],"unfeasible.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2022-10-05T00:00:00"}