{"id":"https://openalex.org/W1979462644","doi":"https://doi.org/10.1145/2020408.2020500","title":"Direct local pattern sampling by efficient two-step random procedures","display_name":"Direct local pattern sampling by efficient two-step random procedures","publication_year":2011,"publication_date":"2011-08-21","ids":{"openalex":"https://openalex.org/W1979462644","doi":"https://doi.org/10.1145/2020408.2020500","mag":"1979462644"},"language":"en","primary_location":{"id":"doi:10.1145/2020408.2020500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publica.fraunhofer.de/documents/N-194550.html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047835257","display_name":"Mario Boley","orcid":"https://orcid.org/0000-0002-0704-4968"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210098248","display_name":"Fraunhofer Institute for Algorithms and Scientific Computing","ror":"https://ror.org/00trw9c49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210098248","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mario Boley","raw_affiliation_strings":["Fraunhofer IAIS and University of Bonn, Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS and University of Bonn, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210098248","https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030358452","display_name":"Claudio Lucchese","orcid":"https://orcid.org/0000-0002-2545-0425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claudio Lucchese","raw_affiliation_strings":["I.S.T.I.-C.N.R. Pisa , Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I.S.T.I.-C.N.R. Pisa , Pisa, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026988137","display_name":"Daniel Paurat","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210098248","display_name":"Fraunhofer Institute for Algorithms and Scientific Computing","ror":"https://ror.org/00trw9c49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210098248","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Paurat","raw_affiliation_strings":["Fraunhofer IAIS and University of Bonn, Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS and University of Bonn, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210098248","https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025793777","display_name":"Thomas G\u00e4rtner","orcid":"https://orcid.org/0000-0001-5985-9213"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210098248","display_name":"Fraunhofer Institute for Algorithms and Scientific Computing","ror":"https://ror.org/00trw9c49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210098248","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas G\u00e4rtner","raw_affiliation_strings":["Fraunhofer IAIS and University of Bonn, Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS and University of Bonn, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210098248","https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9918000102043152,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9829000234603882,"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/computer-science","display_name":"Computer science","score":0.6544447541236877},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6272138357162476},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5938779711723328},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5889184474945068},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.577180027961731},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5377848744392395},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5193830132484436},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4770899713039398},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43212002515792847},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41688451170921326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3230653405189514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2683244049549103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2614741921424866},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18304219841957092},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.140869140625},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1305774450302124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6544447541236877},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6272138357162476},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5938779711723328},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5889184474945068},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.577180027961731},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5377848744392395},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5193830132484436},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4770899713039398},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43212002515792847},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41688451170921326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3230653405189514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2683244049549103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2614741921424866},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18304219841957092},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.140869140625},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1305774450302124},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/2020408.2020500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:dnet:people______::e35a8360a5427e419cc127c04a7ac5e3","is_oa":false,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::e35a8360a5427e419cc127c04a7ac5e3","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD'11, pp. 582\u2013590, San Diego, USA, 21-24 August 2011","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:oai:fraunhofer.de:N-194550","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-194550.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IAIS","raw_type":"conferenceObject"},{"id":"pmh:oai:iris.unive.it:10278/3692242","is_oa":false,"landing_page_url":"http://hdl.handle.net/10278/3692242","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:publica.fraunhofer.de:publica/373478","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/373478","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":{"id":"pmh:oai:fraunhofer.de:N-194550","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-194550.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IAIS","raw_type":"conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2325242462","display_name":null,"funder_award_id":"EU-FP7","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2987902573","display_name":"Using Local Inference in Massively Distributed Systems","funder_award_id":"255951","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W131336165","https://openalex.org/W1484732323","https://openalex.org/W1531636427","https://openalex.org/W1536830218","https://openalex.org/W1536950352","https://openalex.org/W1549565124","https://openalex.org/W1553696291","https://openalex.org/W1565746575","https://openalex.org/W1576562444","https://openalex.org/W1588961056","https://openalex.org/W1985408389","https://openalex.org/W2029817244","https://openalex.org/W2038812321","https://openalex.org/W2089211037","https://openalex.org/W2094500233","https://openalex.org/W2103459555","https://openalex.org/W2104731482","https://openalex.org/W2108419107","https://openalex.org/W2115482638","https://openalex.org/W2116396873","https://openalex.org/W2117169652","https://openalex.org/W2143211346","https://openalex.org/W2151424115","https://openalex.org/W2153472243","https://openalex.org/W2153747975","https://openalex.org/W2154553070","https://openalex.org/W2155325661","https://openalex.org/W2997546679","https://openalex.org/W3120740533","https://openalex.org/W4252115301"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2561315646","https://openalex.org/W2332386680","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W4205698120","https://openalex.org/W4239246781","https://openalex.org/W2542825942","https://openalex.org/W3201620972","https://openalex.org/W1496421768"],"abstract_inverted_index":{"We":[0],"present":[1],"several":[2],"exact":[3],"and":[4,32,105,126],"highly":[5],"scalable":[6],"local":[7,20],"pattern":[8,21,42,80],"sampling":[9,47,65],"algorithms.":[10,66],"They":[11],"can":[12,33,96,115],"be":[13],"used":[14],"as":[15,37,39,81,83],"an":[16,74,84],"alternative":[17],"to":[18,100,123,130],"exhaustive":[19],"discovery":[22,43],"methods":[23,72],"(e.g,":[24],"frequent":[25,124],"set":[26],"mining":[27],"or":[28],"optimistic-estimator-based":[29],"subgroup":[30],"discovery)":[31],"substantially":[34],"improve":[35,116],"efficiency":[36],"well":[38,82],"controllability":[40],"of":[41,69,88,119,135],"processes.":[44],"While":[45],"previous":[46],"approaches":[48],"mainly":[49],"rely":[50],"on":[51],"the":[52,89,93,117],"Markov":[53],"chain":[54],"Monte":[55],"Carlo":[56],"method,":[57],"our":[58],"procedures":[59,114],"are":[60,73],"direct,":[61],"i.e.,":[62],"non":[63],"process-simulating,":[64],"The":[67],"advantages":[68],"these":[70,113],"direct":[71],"almost":[75],"optimal":[76],"time":[77],"complexity":[78],"per":[79],"exactly":[85],"controlled":[86],"distribution":[87],"produced":[90],"patterns.":[91],"Namely,":[92],"proposed":[94],"algorithms":[95],"sample":[97],"(item-)sets":[98],"according":[99],"frequency,":[101,104],"area,":[102],"squared":[103],"a":[106],"class":[107],"discriminativity":[108],"measure.":[109],"Experiments":[110],"demonstrate":[111],"that":[112],"accuracy":[118],"pattern-based":[120],"models":[121],"similar":[122],"sets":[125],"often":[127],"also":[128],"lead":[129],"substantial":[131],"gains":[132],"in":[133],"terms":[134],"scalability.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}