{"id":"https://openalex.org/W2126920781","doi":"https://doi.org/10.1145/1081870.1081887","title":"Fast discovery of unexpected patterns in data, relative to a Bayesian network","display_name":"Fast discovery of unexpected patterns in data, relative to a Bayesian network","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2126920781","doi":"https://doi.org/10.1145/1081870.1081887","mag":"2126920781"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081887","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-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/A5068666126","display_name":"Szymon Jaroszewicz","orcid":"https://orcid.org/0000-0001-9327-5019"},"institutions":[{"id":"https://openalex.org/I104588304","display_name":"University of Szczecin","ror":"https://ror.org/05vmz5070","country_code":"PL","type":"education","lineage":["https://openalex.org/I104588304"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Szymon Jaroszewicz","raw_affiliation_strings":["Technical University of Szczecin, Szczecin, Poland"],"affiliations":[{"raw_affiliation_string":"Technical University of Szczecin, Szczecin, Poland","institution_ids":["https://openalex.org/I104588304"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007427935","display_name":"Tobias Scheffer","orcid":"https://orcid.org/0000-0003-4405-7925"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Scheffer","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","[Humboldt Universitat zu Berlin, Berlin, Germany]"],"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"[Humboldt Universitat zu Berlin, Berlin, Germany]","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068666126"],"corresponding_institution_ids":["https://openalex.org/I104588304"],"apc_list":null,"apc_paid":null,"fwci":15.2649,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98625147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9988999962806702,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8053942918777466},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.6962677836418152},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6684107780456543},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6021243929862976},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5574942827224731},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4746744632720947},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44484785199165344},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.43218228220939636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4073140621185303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37178969383239746},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1511055827140808},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10154539346694946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8053942918777466},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.6962677836418152},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6684107780456543},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6021243929862976},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5574942827224731},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4746744632720947},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44484785199165344},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.43218228220939636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4073140621185303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37178969383239746},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1511055827140808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10154539346694946},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1081870.1081887","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1489843519","https://openalex.org/W1498810706","https://openalex.org/W1517928879","https://openalex.org/W1526796402","https://openalex.org/W1553696291","https://openalex.org/W1592987584","https://openalex.org/W1597561788","https://openalex.org/W1755360231","https://openalex.org/W1973996621","https://openalex.org/W2023139942","https://openalex.org/W2031355581","https://openalex.org/W2042970816","https://openalex.org/W2089624555","https://openalex.org/W2097508937","https://openalex.org/W2120943950","https://openalex.org/W2130072301","https://openalex.org/W2130416410","https://openalex.org/W2138745909","https://openalex.org/W2153747975","https://openalex.org/W2165962877","https://openalex.org/W2172186225","https://openalex.org/W2346626577","https://openalex.org/W3124607078","https://openalex.org/W3197806025","https://openalex.org/W6635637936"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W1508895727","https://openalex.org/W4254477493","https://openalex.org/W2149300931","https://openalex.org/W2505556904"],"abstract_inverted_index":{"We":[0,87],"consider":[1],"a":[2,9,19,25,58,89],"model":[3],"in":[4,16,22,57],"which":[5],"background":[6],"knowledge":[7],"on":[8,99],"given":[10],"domain":[11],"of":[12,18,92],"interest":[13],"is":[14,31,38,50,75],"available":[15],"terms":[17],"Bayesian":[20,59,106],"network,":[21],"addition":[23],"to":[24,32,39],"large":[26],"database.":[27,47,68],"The":[28],"mining":[29],"problem":[30,49],"discover":[33],"unexpected":[34,85],"patterns:":[35],"our":[36],"goal":[37],"find":[40],"the":[41,63,81,93],"strongest":[42],"discrepancies":[43],"between":[44],"network":[45,60],"and":[46,61,77,102,108],"This":[48],"intrinsically":[51],"difficult":[52],"because":[53],"it":[54],"requires":[55],"inference":[56],"processing":[62],"entire,":[64],"potentially":[65],"very":[66],"large,":[67],"A":[69],"sampling-based":[70],"method":[71],"that":[72],"we":[73],"introduce":[74],"efficient":[76],"yet":[78],"provably":[79],"finds":[80],"approximately":[82],"most":[83],"interesting":[84],"patterns.":[86],"give":[88],"rigorous":[90],"proof":[91],"method's":[94],"correctness.":[95],"Experiments":[96],"shed":[97],"light":[98],"its":[100],"efficiency":[101],"practicality":[103],"for":[104],"large-scale":[105],"networks":[107],"databases.":[109]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}