{"id":"https://openalex.org/W3036474431","doi":"https://doi.org/10.1145/3385653","title":"MiSoSouP","display_name":"MiSoSouP","publication_year":2020,"publication_date":"2020-06-21","ids":{"openalex":"https://openalex.org/W3036474431","doi":"https://doi.org/10.1145/3385653","mag":"3036474431"},"language":"en","primary_location":{"id":"doi:10.1145/3385653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3385653","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-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/A5021368473","display_name":"Matteo Riondato","orcid":"https://orcid.org/0000-0003-2523-4420"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matteo Riondato","raw_affiliation_strings":["Amherst College, East Drive, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"Amherst College, East Drive, Amherst, MA","institution_ids":["https://openalex.org/I177605424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060279781","display_name":"Fabio Vandin","orcid":"https://orcid.org/0000-0003-2244-2320"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Vandin","raw_affiliation_strings":["Universit\u00e0 di Padova, Via G. Gradenigo, Padova, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Padova, Via G. Gradenigo, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021368473"],"corresponding_institution_ids":["https://openalex.org/I177605424"],"apc_list":null,"apc_paid":null,"fwci":1.3345,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85867007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":"5","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"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":0.9973999857902527,"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/suite","display_name":"Suite","score":0.6426381468772888},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6248923540115356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5782591104507446},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5320473909378052},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.5237293839454651},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5022873878479004},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5005359649658203},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4619711935520172},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3968248665332794},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3571292757987976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3482203483581543},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28984516859054565}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6426381468772888},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6248923540115356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5782591104507446},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5320473909378052},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.5237293839454651},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5022873878479004},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5005359649658203},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4619711935520172},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3968248665332794},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3571292757987976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3482203483581543},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28984516859054565},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3385653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3385653","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:www.research.unipd.it:11577/3351679","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/3351679","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2399976439","display_name":null,"funder_award_id":"SID2017 and STARS","funder_id":"https://openalex.org/F4320321966","funder_display_name":"Universit\u00e0 degli Studi di Padova"}],"funders":[{"id":"https://openalex.org/F4320321966","display_name":"Universit\u00e0 degli Studi di Padova","ror":"https://ror.org/00240q980"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W15476721","https://openalex.org/W135524293","https://openalex.org/W1791352925","https://openalex.org/W1991417304","https://openalex.org/W2000131178","https://openalex.org/W2055400097","https://openalex.org/W2078825395","https://openalex.org/W2087258353","https://openalex.org/W2090479884","https://openalex.org/W2104579579","https://openalex.org/W2144098707","https://openalex.org/W2153747975","https://openalex.org/W2156821882","https://openalex.org/W2338621248","https://openalex.org/W2404544029","https://openalex.org/W2523484136","https://openalex.org/W2566871804","https://openalex.org/W2809301005","https://openalex.org/W2884593183","https://openalex.org/W2899702797","https://openalex.org/W3015364522","https://openalex.org/W4230674625","https://openalex.org/W4233413206","https://openalex.org/W4236362309","https://openalex.org/W4246350460","https://openalex.org/W4292025355"],"related_works":["https://openalex.org/W4388813866","https://openalex.org/W2999104021","https://openalex.org/W1481656249","https://openalex.org/W2850804095","https://openalex.org/W2162280767","https://openalex.org/W3047225376","https://openalex.org/W1570799877","https://openalex.org/W2800688113","https://openalex.org/W4236933217","https://openalex.org/W2057598446"],"abstract_inverted_index":{"We":[0,30,51,79],"present":[1],"MiSoSouP,":[2],"a":[3,23,27,32,56],"suite":[4],"of":[5,11,26,35,40,74,87,97,101,104,106,139],"algorithms":[6,127],"for":[7],"extracting":[8],"high-quality":[9,72],"approximations":[10],"the":[12,65,75,85,88,98,102,129,137,143],"most":[13,76],"interesting":[14,77],"subgroups,":[15],"according":[16],"to":[17,46,64,69,113],"different":[18],"popular":[19],"interestingness":[20],"measures,":[21],"from":[22,59],"random":[24],"sample":[25,66,115],"transactional":[28],"dataset.":[29,145],"describe":[31],"new":[33],"formulation":[34],"these":[36],"measures":[37],"as":[38],"functions":[39],"averages,":[41],"that":[42,123],"makes":[43],"it":[44,133],"possible":[45],"approximate":[47],"them":[48],"using":[49],"sampling.":[50],"then":[52,111],"discuss":[53],"how":[54],"pseudodimension,":[55],"key":[57],"concept":[58],"statistical":[60],"learning":[61],"theory,":[62],"relates":[63],"size":[67],"needed":[68],"obtain":[70],"an":[71,81],"approximation":[73],"subgroups.":[78],"prove":[80],"upper":[82,109],"bound":[83,110],"on":[84,94,119],"pseudodimension":[86],"problem":[89],"at":[90],"hand,":[91],"which":[92],"depends":[93],"characteristic":[95],"quantities":[96],"dataset":[99],"and":[100,132],"language":[103],"patterns":[105],"interest.":[107],"This":[108],"leads":[112],"small":[114],"sizes.":[116],"Our":[117],"evaluation":[118],"real":[120],"datasets":[121],"shows":[122],"MiSoSouP":[124],"outperforms":[125],"state-of-the-art":[126],"offering":[128],"same":[130],"guarantees,":[131],"vastly":[134],"speeds":[135],"up":[136],"discovery":[138],"subgroups":[140],"w.r.t.":[141],"analyzing":[142],"whole":[144]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-06-25T00:00:00"}